# The Transfer Neurons Hypothesis: An Underlying Mechanism for Language Latent Space Transitions in Multilingual LLMs

arXiv: https://arxiv.org/abs/2509.17030 · HTML: https://mlsanity.com/paper/2509.17030/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Sep 2025.

## Built on by (most cited first, 8 of 8)

- [Cross-Lingual Activation Steering for Multilingual Language Models](https://mlsanity.com/paper/2601.16390/) (2026)
- [When Meanings Meet: Investigating the Emergence and Quality of Shared Concept Spaces during Multilingual Language Model Training](https://mlsanity.com/paper/2601.22851/) (2026)
- [Latent-Space Intervention for Cross-Lingual Factual Consistency: Consistency Improvements without Accuracy Drops](https://mlsanity.com/paper/2608.28860/) (2026)
- [Shared Doubt: Zero-Shot Cross-Lingual Confidence Estimation for Language Models](https://mlsanity.com/paper/2605.31220/) (2026)
- [Test, then Route: How Language Models Execute In-Context Conditional Rules Across Models and Languages](https://mlsanity.com/paper/2608.04183/) (2026)
- [Discovering Cross-Language Reasoning Invariance in LLMs with Geometry-Invariant Sparse Autoencoders](https://mlsanity.com/paper/2608.23809/) (2026)
- [Cross-lingual Functional Vectors for Emotion Detection in Large Language Models](https://mlsanity.com/paper/2608.29613/) (2026)
- [Target-Language Generation in Multilingual Models: Activation Steering and Optimal Control](https://mlsanity.com/paper/2609.16967/) (2026)

## Abstract (arXiv)

Recent studies have suggested a processing framework for multilingual inputs in decoder-based LLMs: early layers convert inputs into English-centric and language-agnostic representations; middle layers perform reasoning within an English-centric latent space; and final layers generate outputs by transforming these representations back into language-specific latent spaces. However, the internal dynamics of such transformation and the underlying mechanism remain underexplored. Towards a deeper understanding of this framework, we propose and empirically validate The Transfer Neurons Hypothesis: certain neurons in the MLP module are responsible for transferring representations between language-specific latent spaces and a shared semantic latent space. Furthermore, we show that one function of language-specific neurons, as identified in recent studies, is to facilitate movement between latent spaces. Finally, we show that transfer neurons are critical for reasoning in multilingual LLMs.