Research watch · Paper · Jul 2026

Multilingual Sparse Autoencoders and Principled Layer Selection for Cross-Lingual Steering in Large Language Models

This paper studies sparse autoencoders for feature-level interpretability and steering in multilingual language models. It also proposes a more principled way to choose which layers to target for control.

Our reading

From: ACL Anthology

The authors test SAE-based language control in multilingual settings where English-only SAEs often transfer poorly.

They show that steering quality depends heavily on layer choice and multilingual training choices.

It does not demonstrate self-introspection, accurate report of internal states, or anything about consciousness.

Source: ACL Anthology ↗. This is a summary; the source is the authority.

What it changes

This adds evidence that SAE-based control can work across languages, but it does not change the evidential status of model experiences.

How we weigh evidence like this: the evidence levels.