© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    NLAsNatural Language Autoencoders
    Fraser-Taliente, Kantamneni, Ong et al. 2026
    Paper
    BlogCode
    Contact
    Start ChatSet up a scenario to analyze the model's thoughts.
    Choose DemoClick one of the demos at the top to load a scenario.
    Token Selection
    Special Tokens
    Explanation by activation verbalizer
    Explanations generated by the activation verbalizer will appear here.
    NLAs can produce unexpected or incorrect explanations. See limitations.