© 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. 1328
    Prev
    Next
    INDEX
    Explanations

    python programming or libraries

    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
    ÏĢιÏĥ
    -0.08
    /dis
    -0.07
    ities
    -0.07
    åĮ»åѦéĻ¢
    -0.07
    pps
    -0.07
    ments
    -0.07
    å¦Ĥå±±
    -0.06
    оваÑĤÑĮ
    -0.06
    utm
    -0.06
    èģĺçĶ¨äººåijĺ
    -0.06
    POSITIVE LOGITS
    aceous
    0.10
    à¹ģลà¸Ļà¸Ķà¹Į
    0.09
    .raises
    0.09
    sev
    0.08
    ramid
    0.08
    icket
    0.08
    onga
    0.08
    ÙĪØŃ
    0.08
    icity
    0.08
    ardy
    0.08
    Activations Density 0.087%

    No Known Activations