© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 58851
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
    ux
    -0.07
    è´§çī©è¿IJè¾ĵ
    -0.07
    æįķ
    -0.07
    欣
    -0.07
    shine
    -0.06
     K
    -0.06
    วย
    -0.06
    è©°ãĤģ
    -0.06
    K
    -0.06
    gather
    -0.06
    POSITIVE LOGITS
    éģŀ
    0.08
    Sos
    0.08
    icode
    0.08
    æ¦Ľ
    0.08
    ocode
    0.08
    RAY
    0.07
    æīĢæĮģ
    0.07
    колÑĮ
    0.07
    浩çĢļ
    0.07
    浩
    0.07
    Activations Density 0.001%

    No Known Activations