© 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. 57942
    Prev
    Next
    INDEX
    Explanations

    ethyl

    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
    åĨĹ
    -0.07
    ä¸Ń人
    -0.07
    اØŃ
    -0.07
    hong
    -0.07
    éļĽ
    -0.07
    erait
    -0.07
    sche
    -0.07
    opl
    -0.07
    lus
    -0.07
    кÑĢи
    -0.06
    POSITIVE LOGITS
    ield
    0.07
    naud
    0.07
    ulty
    0.07
    @email
    0.07
    âtre
    0.07
    ç»ıæľ¬éĻ¢
    0.07
    ä¸İæŶ
    0.06
    {}\
    0.06
    人æīįç½ij
    0.06
    à¸Ľà¸ģ
    0.06
    Activations Density 0.033%

    No Known Activations