© 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. 45035
    Prev
    Next
    INDEX
    Explanations

    scheme

    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
    ureka
    -0.07
    nich
    -0.07
     again
    -0.06
    leon
    -0.06
    èĦı
    -0.06
    宾
    -0.06
    ç»ıèIJ¥æ¨¡å¼ı
    -0.06
    CB
    -0.06
     Sultan
    -0.06
    fur
    -0.06
    POSITIVE LOGITS
    å¿Ĺæĺİ
    0.08
     Demi
    0.07
     Beri
    0.07
    ä¸İæľ¬ç«Ļ
    0.07
    ãħİãħİ
    0.07
    .http
    0.07
    ä¸īåĢį
    0.07
    صد
    0.07
     demi
    0.07
    /documentation
    0.07
    Activations Density 0.006%

    No Known Activations