# Goodfire finds neurons in Qwen3.6-35B-A3B are sparse and interpretable

> Original title: Neurons as an Interpretable Basis

- Source: Goodfire Research
- Published: 2026-11-10T05:00:00.000Z
- Bad Influence: https://badinfluence.news/items/biu81cg6azdna7s1ounbl14tu
- Original: https://www.goodfire.com/research/neurons-as-an-interpretable-basis

## Summary

Goodfire reports that ablating the 92.2% weakest MoE neuron activations in Qwen3.6-35B-A3B has only modest effects, a 2.9% increase in language model loss. The team says most neurons have one dominant computational mode and can be described in natural language, with descriptions predicting firing with 95% accuracy against random text.

## Why it matters

The paper tests whether neurons are a usable analysis unit by ablating 92.2% of weak activations and describing neurons in natural language, giving a concrete method for interpretability work.