© 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. 34544
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    åı£æ°´
    -0.07
    æľ¬é¡µ
    -0.07
    asco
    -0.07
    ksom
    -0.07
    åѤåĦ¿
    -0.06
    avais
    -0.06
    ç»´æĸ¯
    -0.06
    Ìģ
    -0.06
    ynet
    -0.06
    ooth
    -0.06
    POSITIVE LOGITS
    ingly
    0.07
    ãģ®æĸ¹ãģ¯
    0.07
    éĻµ
    0.07
    è¿ĽåĪ°
    0.07
    éĻµåİ¿
    0.07
    pective
    0.07
    ç¾İ
    0.07
    继ç»Ńåľ¨
    0.06
    èĮī
    0.06
    idio
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.