© 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. 20896
    Prev
    Next
    INDEX
    Explanations

    using directives followed by č

    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
    otin
    -0.08
     ká»ī
    -0.08
    iolet
    -0.07
    uela
    -0.07
    اÙĨت
    -0.07
    ader
    -0.07
    oton
    -0.07
    otropic
    -0.07
    idf
    -0.06
    æĪij为群ä¼ĹåĬŀå®ŀäºĭ
    -0.06
    POSITIVE LOGITS
    stral
    0.09
    ste
    0.08
    à¥įस
    0.07
    str
    0.07
    esar
    0.07
    lore
    0.07
    иÑģÑĤÑĢи
    0.07
    سازÛĮ
    0.07
    sp
    0.06
    sth
    0.06
    Activations Density 0.001%

    No Known Activations