© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 401
    Prev
    Next
    INDEX
    Explanations

    licenses and code

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/qwen2.5-7B-it-layer-20-saes/pile/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erable
    -0.23
    ancellable
    -0.22
    ipop
    -0.21
    åīįæīĢæľªæľī
    -0.21
    uib
    -0.20
    unicipio
    -0.20
    aname
    -0.20
    richt
    -0.20
    duino
    -0.20
    blr
    -0.20
    POSITIVE LOGITS
     NavLink
    0.21
     //!<
    0.21
    æļ¨
    0.20
    åľ¨çº¿åĴ¨è¯¢
    0.20
     ///<
    0.19
     Joi
    0.18
     /*!<
    0.18
     /**<
    0.18
    以åıĬåħ¶ä»ĸ
    0.18
    èĩŁ
    0.18
    Activations Density 7.583%

    No Known Activations