© 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. 60909
    Prev
    Next
    INDEX
    Explanations

    immunology studies

    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
    ç¿İ
    -0.07
    CAT
    -0.07
    ogi
    -0.07
     vertreten
    -0.07
    äºĮçĻ¾
    -0.07
    ONTAL
    -0.06
    unami
    -0.06
    大éĺŁéķ¿
    -0.06
    æľ¬æĸĩéĵ¾æİ¥
    -0.06
    ä¸įåĩĨ
    -0.06
    POSITIVE LOGITS
    lsi
    0.07
    LIK
    0.07
    _slide
    0.07
    æĺİç¡®
    0.07
    áĥIJáĥĽ
    0.06
    à¶Ńà·Ķ
    0.06
    对被
    0.06
    ç¨³åĽº
    0.06
    æºľ
    0.06
    olik
    0.06
    Activations Density 0.004%

    No Known Activations