Skip to content
Igor Bogdanov

Interpretability

Discovering Cross-Language Reasoning Invariance in LLMs

Shared geometry across languages may reveal common reasoning structure, but representational similarity alone does not establish causal interchangeability.

Venue
Workshop paperICML 2026 Workshop on Mechanistic Interpretability
Role
First author · method · analysis pipeline
Themes
  • Interpretability
gi-sae pipeline
GI-SAE pipeline: multilingual reasoning activations, geometry-invariant sparse autoencoder, geometry metrics, causal interventions, and sharing regimesgi-sae · geometry vs. function across languagesParallel reasoning promptssame task, many languagesResidual-stream activationsfixed layerGI-SAEgeometry-invariant featuresShared dictionarycomparable across languagesGeometry metricsalignment · similarityCausal interventionswap · ablate across languagesconvergent · aligned and interchangeablesaturated · aligned, not interchangeablelow-sharing · language-specificsharing regimes (joint reading)similarity alone does not establish functional interchangeability

Pipeline: parallel reasoning prompts in several languages produce residual-stream activations at a fixed layer. A geometry-invariant sparse autoencoder learns a shared dictionary. From the dictionary, geometry metrics measure alignment and causal interventions swap or ablate features across languages. The joint reading assigns feature groups to convergent, saturated, or low-sharing regimes.

GI-SAE
geometry-invariant sparse autoencoder
features trained to be invariant to per-language geometric transforms
Causal
intervention design
swap and ablate features across languages and measure downstream reasoning
3
sharing regimes
convergent, saturated, and low-sharing

01

The problem

If a language model reasons the same way in two languages, its internal representations of that reasoning should be shared. Most evidence for sharing is geometric: activations for parallel inputs line up after a rotation or projection. But geometric alignment is a weak test. Two sets of features can be similar in shape and still do different work when the model actually reasons.

This project asks a sharper question: are the features that carry reasoning in one language functionally interchangeable with those in another? Answering it requires a feature basis that is not an artefact of one language's geometry, and an intervention that tests function rather than similarity.

Held constant across languages: the reasoning task, the prompt structure, and the model layer under analysis. Varied: the language of the prompt and, in interventions, the source language of the features injected.

02

System and method

The GI-SAE analysis pipeline. Parallel reasoning prompts in several languages produce residual-stream activations. A geometry-invariant sparse autoencoder learns a shared feature dictionary that tolerates per-language transforms. Geometry metrics quantify alignment. Causal interventions swap or ablate features across languages and measure the effect on reasoning outputs. The joint reading assigns each feature group to a convergent, saturated, or low-sharing regime.

↑ Figure: gi-sae pipeline

03

Experimental design

Research question
Do LLMs reuse common reasoning structure across languages, and is it causally interchangeable?
Method
Geometry-invariant sparse autoencoders trained over parallel multilingual reasoning activations
Language and model setup
Parallel reasoning prompts across multiple languages on open-weight models · the exact language and model list is specified in the paper
Geometry metrics
Alignment and similarity measures between per-language feature geometries
Causal intervention design
Cross-language feature swaps and ablations with downstream reasoning accuracy as the outcome
Regimes
Convergent (shared and interchangeable), saturated (aligned but not interchangeable), and low-sharing

04

Main findings

  1. 01

    Geometric alignment and causal interchangeability are different questions

    Feature groups can align closely in geometry while cross-language swaps change reasoning behaviour, and vice versa. The two measurements disagree often enough that neither can stand in for the other.

    Why it mattersClaims of 'shared multilingual reasoning' based on similarity alone should be read as hypotheses, not conclusions.

  2. 02

    Sharing is organised into regimes rather than a single degree

    Feature groups fall into convergent, saturated, and low-sharing regimes that differ in both alignment and causal transferability.

    Why it mattersA model can be multilingual in some reasoning components and language-specific in others. Interpretability tooling should report which is which.

  3. 03

    Geometry-invariant training yields a usable cross-language dictionary

    Training the sparse autoencoder to be invariant to per-language transforms produces features that can be compared and intervened on across languages without hand-aligning bases.

    Why it mattersGI-SAE makes causal cross-language probing tractable as a routine analysis step.

05

What I built

The engineering behind the result. Every number above was produced by systems I designed and implemented.

  • Activation capture

    Hooks for collecting residual-stream activations on parallel multilingual reasoning prompts.

  • GI-SAE training

    Sparse-autoencoder training with geometry-invariance constraints on GPU.

  • Geometry metrics

    Alignment and similarity computations between per-language feature geometries.

  • Intervention harness

    Cross-language feature swap and ablation with automated evaluation of downstream reasoning.

  • Analysis pipeline

    Regime assignment and figure generation from intervention results.

06

Limitations

Contact

Building reliable AI systems requires both research and engineering.

I’m interested in research engineering, applied research, agent infrastructure, evaluation, reliability, interpretability, and research-to-production work.

Send a message

Opens your mail client with the message prefilled. Nothing is stored on this site.