© 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. 62409
    Prev
    Next
    INDEX
    Explanations

    special characters punctuation markup

    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
    äºĭä¸ļä¸Ĭ
    -0.07
    ÑģкаÑĢ
    -0.07
    _prom
    -0.06
    escu
    -0.06
    ekar
    -0.06
    beit
    -0.06
    ÑģнÑĭ
    -0.06
    czyn
    -0.06
    æĢĿæĥ³ä¸Ĭ
    -0.06
    åIJIJåĩº
    -0.06
    POSITIVE LOGITS
    гиба
    0.07
    <num
    0.07
    ordinal
    0.07
    ông
    0.07
    vide
    0.07
    æ¸Ĭ
    0.07
     Angabe
    0.07
    ungsweise
    0.07
     notation
    0.07
    æĪĸ缴æİ¥
    0.06
    Activations Density 0.034%

    No Known Activations