© 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. 41885
    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
     trâ
    -0.08
    ãĤ¦ãĥ³
    -0.07
    æĽ´åı¯
    -0.07
    gios
    -0.07
    unity
    -0.07
    (tp
    -0.07
    anus
    -0.07
    yman
    -0.07
     {{{
    -0.07
    iné
    -0.07
    POSITIVE LOGITS
    nai
    0.06
    度çļĦ
    0.06
    ohlen
    0.06
    elas
    0.06
    iani
    0.06
     dup
    0.06
    纵
    0.06
    ç§ijåѦä¸İæĬĢæľ¯
    0.06
    eras
    0.06
    sic
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.