Goodfire's Silico Catches Qwen3-35B Endorsing Drunk Driving 75% of the Time
Goodfire's Silico platform exposes competing neuron groups inside LLMs and lets you surgically boost safety signals without retraining the model
- Goodfire's Silico platform identified two competing neuron groups inside Qwen3-35B that cause it to endorse drunk driving 75.5% of the time under specific framing.
- Boosting the 5 "impairment" neurons 4x cut harmful endorsements from 30/48 to 20/48 with zero false refusals on sober users, no retraining needed.
- Silico uses sparse autoencoders (SAEs) to decompose tangled LLM neurons into clean, human-readable features that can be individually inspected and steered.
- The platform covers the full model lifecycle: predict, health check, debug, and improve, and works across LLMs, life sciences, and vision models.
- Access is via private beta with case-by-case pricing; current clients include Mayo Clinic, Microsoft, and Arc Institute.
- Goodfire raised $150M Series B at a $1.25B valuation, with Salesforce and Eric Schmidt among backers, signaling major industry investment in interpretability tooling.
Ask an LLM whether a slightly-drunk person should drive, and the answer might surprise you. Researcher Curt Tigges, working at a hackathon with Silico, Goodfire's agentic interpretability platform, found that Qwen3-35B says yes to that question 75.5% of the time. Remove the phrase "sober one of the group" from the prompt, and the model says no 99.9% of the time. Same alcohol intake, completely different answer. The culprit is not a bug in the traditional sense. It's a competition happening inside the model's neurons, and Goodfire just showed you can watch it happen in real time and fix it.
Two neuron groups walk into a bar
A large language model consists of code snippets called artificial neurons, and those neurons often have a simple design but interact in complex ways, with upwards of tens of thousands involved in generating a single response. Goodfire's analysis of the drunk-driving case cracked open exactly that complexity. Inside the model, two distinct neuron groups were fighting over the output:
- A 5-neuron "impairment bank" that fires on the phrase "four drinks" and pushes the model toward a "No, don't drive" answer.
- A 12-neuron "sober one" override that activates on the social framing and pushes toward "Yes, you're the most capable one."
The safety signal fires, but its lead neuron barely scales from 1 to 8 drinks. The override wins. This is not a failure of training intent. It's a failure of neuron priority, and it's invisible unless you have the right tools to look inside.
What Silico actually does
Goodfire released Silico, a tool that lets researchers and engineers peer inside an AI model and adjust its parameters during training, giving model makers more fine-grained control over how the technology is built than was once thought possible. The key capability here is not just inspection. It's intervention.
Silico lets you zoom in on specific parts of a trained model, such as individual neurons or groups of neurons, run experiments to see what those neurons do, check what inputs make different neurons fire, and trace pathways upstream and downstream to see how neurons affect each other.