Podcast, The Cognitive Revolution
The Neuron Basis: Goodfire's Curt Tigges on Agentic Interp, Monosemanticity & Reverse Engineering
Hosted by Nathan Labenz
About
Curt Tigges of Goodfire discusses research showing that individual MLP neurons in modern language models are more interpretable than the field assumed: few need to be active at once, and a neuron with several meanings usually carries a compact set rather than hundreds. He explains how gated MLPs let neurons act as legible conjunctions and control signals, how an automated agent tests neuron hypotheses across architectures such as Qwen3.6-35B-A3B, and how extensive dynamic sparsity without lasting benchmark loss offers an alternative to external featurizers for behaviour monitoring and persona steering.
Topics
- MLP neurons, broader topic: neurons
- language models
- Monosemanticity, search World Wide
- gated MLPs, search World Wide
- automated agent, search World Wide
- Qwen3.6-35B-A3B, search World Wide
- dynamic sparsity, broader topic: sparsity
- behaviour monitoring, broader topic: monitoring
- persona steering, broader topic: steering