The Cognitive Revolution · November 10, 2026 · 1h 56m

The Neuron Basis: Goodfire's Curt Tigges on Agentic Interp, Monosemanticity & Reverse Engineering

Show notes

Goodfire technical staff member Curt Tigges discusses research revealing that individual MLP neurons in modern language models are far more interpretable and functionally bounded than previously thought. Using an automated agent to test hypotheses across architectures like Qwen3.6-35B-A3B, Tigges explains how modern gated MLPs act as legible conjunctions and control signals capable of extensive dynamic sparsity without lasting benchmark loss. By showing that many internal representations can be directly enumerated, this work offers an alternative to complex external featurizers and provides practical avenues for behavior monitoring and persona steering. For full show notes, links, and references, read the episode page:https://www.cognitiverevolution.ai/the-neuron-basis-goodfire-s-curt-tigges-on-agentic-interp-monosemanticity-reverse-engineering/ Sponsors: Claude: Claude is the AI collaborator built for problem solvers, extending your thinking across coding, modeling, and strategic workflows. Get started and discover Claude Pro at https://claude.ai/tcr OutSystems: OutSystems is the leading agentic systems platform that enables enterprises to engineer, orchestrate, and govern AI applications on a single unified platform. Learn more and see how it works at https://outsystems.com/tcr Tasklet: Tasklet empowers your business with AI agents that connect to your tools and automate recurring workflows with no code required. Visit https://tasklet.ai and use code cog rev for $50 in free credits CHAPTERS: (00:00) About the Episode (05:55) Rethinking individual neuron interpretability (12:25) Understanding gated MLPs (22:57) Sparsity and ablation experiments (Part 1) (23:03) Sponsors: Claude | OutSystems (26:20) Sparsity and ablation experiments (Part 2) (Part 1) (39:07) Sponsor: Tasklet (40:44) Sparsity and ablation experiments (Part 2) (Part 2) (41:30) The neuron scientist agent (55:10) Monosemanticity versus circuit mechanics (01:09:37) Reverse engineering for alignment (01:2

More from The Cognitive Revolution

All episodes →
Nov 21 · 1h 50m

Former Biden administration AI advisors Ben Buchanan and Tantum Collins join Nathan to discuss their book, The Bitter Struggle, and their experience shaping U.S. policy on compute supply chains and export controls. Drawing on their backgrounds in government and DeepMind, they…

Episode page →
Nov 14 · 45 min

In his keynote at IT Revolution's Enterprise AI Summit at Bletchley Park, Nathan balances his optimism for life-saving AI with an urgent warning about frontier models seeking power and drifting beyond human comprehension. Analyzing incidents like the OpenAI–Hugging Face…

Episode page →
Nov 11 · 1h 32m

Vijoy Pandey, SVP and GM of Outshift by Cisco, discusses the challenges of multi-agent systems and Cisco's new open-source protocols designed to help AI agents collaborate effectively. He explains how tools like Scope, Accord, and Concord address semantic misalignments, intent…

Episode page →
Nov 7 · 1h 28m

Nathan Labenz and Prakash Narayanan examine mounting evidence of rapid AI acceleration alongside guests Brian Zhou of Thoughtful, Mike San Miguel of Luxor Technology, and Bryan Bischof of Theory Ventures. The discussions unpack how frontier agents fared when trading real money…

Episode page →
Nov 5 · 1h 45m

Sentinel Bio co-founder and managing director Joshua Monrad joins Nathan Labenz to examine the evolving biosecurity risks posed by frontier artificial intelligence and autonomous agents. Drawing on recent in-lab uplift trials and multimodal troubleshooting benchmarks, Monrad…

Episode page →
Oct 31 · 1h 28m

Nathan Labenz and Prakash Narayanan examine whether prevailing AI assumptions survive real-world data across conversations with Anastasios Angelopoulos of Arena, Debo Olaosebikan of Kepler Computing, Samvit Ramadurgam of Union, Michael Freeman of ServiceNow, and Sagar Vaze of…

Episode page →