© 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. 21007
    Prev
    Next
    INDEX
    Explanations

    Drinfeld presentation, Manin triple

    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
    ÑĤÑĥÑĢи
    -0.08
     Volg
    -0.08
    utig
    -0.08
    wesen
    -0.08
    èĥĮåIJİçļĦ
    -0.08
    erstellung
    -0.08
    eced
    -0.08
    zzle
    -0.08
    entic
    -0.07
    anim
    -0.07
    POSITIVE LOGITS
    -
    0.08
    's
    0.07
    (
    0.07
    /
    0.07
    ridge
    0.07
    0.07
    owski
    0.06
    ç¬Ķä¸ĭ
    0.06
     Medal
    0.06
    ACA
    0.06
    Activations Density 0.034%

    No Known Activations