What's New
Other Updates
Newsletter Bug: Our email sender had a bug which caused some unsubscribe links to not work as expected. This is now fixed, our apologies.
Browse 8.6 million neuron dashboards via the MLP Neurons release page, or jump to specific models here:
Inference is enabled for several of these models, so you can do the usual activation testing, steering, search by topK, and more.
Here's a TopK search for Qwen3 8B's neurons:
And here's a steer on a Qwen "airplanes" neuron: Neuronpedia now hosts imported explanations from five neuron-explaining platforms onto Neuronpedia, with permission from their authors and links back to the original sources:
Here's the same Qwen3 8B "airplanes" neuron, as explained by three different sources: Notice in the above example that clicking certain explanations changes the top logits to different lists more relevant to that explanation or explanation method. These are "Token Lists", a new feature on Neuronpedia that which show lists of tokens associated with a neuron or latent. Token lists are directly linkable. For example, here's the link showing tokens found via the fitted Jacobian Lens for that same Qwen airplanes neuron: https://www.neuronpedia.org/qwen3-8b/24/2665?tokenlist=jacobian-lens:J-Lens
🙋 Opportunity to Contribute: Want to upload your labels? We have a gated upload API for explanations, available upon request. Contact us and we'll set you up.
ICA Lens revisits independent component analysis as a way to find interpretable directions in the residual stream, with no dictionary training needed.
Neuronpedia hosts ICA Lenses for 6 models. Each lens is for one layer, and the number of directions per lens is the model's hidden size (d_model). Each direction has its own full dashboard, like SAE latents and neurons. Using the dropdown above the logits, you can switch to viewing the tokens through J-Lens or R-Lens as well.
Most ICA lenses are inference enabled, too. For example, here's steering on a "legal system" direction in GPT2-Small (steer link):
Just like with SAEs and neurons, you can use Inference Search to find top directions in a model's ICA lenses using custom text. Here's an inference search with text about food in Italy in Gemma 2 2B IT:
Inspired by the previously featured NP-Feature-Compare by Melissa Wessel, you can now compare two dashboards side by side on Neuronpedia directly.
Here, we compare a neuron in Gemma 4 12B with the same neuron in its instruct variant: The Neuronpedia Workspace Lenses Huggingface has been updated with R-Lens and J++ lens from Bobby Faber. Two J++ lenses are enabled for custom chats on Neuronpedia: gemma-3-12b-it and llama-3.1-8b-it.
As always, please contact us with your questions, feedback, and suggestions.