© 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. 1974
    Prev
    Next
    INDEX
    Explanations

    fashion and style

    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
     trous
    -0.31
     subpo
    -0.27
     perpetr
    -0.27
     seksi
    -0.24
     luxe
    -0.24
     misdemean
    -0.24
     beneficiation
    -0.24
    itat
    -0.23
    åIJĦå¼ıåIJĦæł·
    -0.22
     }}>{
    -0.22
    POSITIVE LOGITS
    建档ç«ĭ
    0.36
    ï¼ł
    0.29
    ä¸ī大éĺ¶æ®µ
    0.29
    /↵↵↵↵
    0.28
     volunte
    0.28
    âļĹ
    0.28
    //č↵č↵
    0.28
    };č↵č↵č↵
    0.26
     (;;
    0.26
    /Foundation
    0.26
    Activations Density 3.715%

    No Known Activations