© 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
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30885
    Prev
    Next
    INDEX
    Explanations

    version numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åIJĦç§įåİŁåĽł
    -0.07
    óf
    -0.07
    ÄŁÃ¼
    -0.07
    ÃĶI
    -0.07
     extraord
    -0.06
    ulare
    -0.06
    rž
    -0.06
    箸
    -0.06
     Frat
    -0.06
    पà¥Ĥरà¥įण
    -0.06
    POSITIVE LOGITS
    pliant
    0.07
    enco
    0.07
    arel
    0.07
    æŃ¥æŃ¥é«ĺ
    0.07
    _TLS
    0.06
    getConfig
    0.06
    env
    0.06
     spiagg
    0.06
    perti
    0.06
    åªĽ
    0.06
    Activations Density 0.017%

    No Known Activations