© 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. 63199
    Prev
    Next
    INDEX
    Explanations

    scrapie, Jr, rence, script

    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
    ulich
    -0.08
    lett
    -0.07
    abh
    -0.06
    è¿Ľå±ķæĥħåĨµ
    -0.06
    ãĥ£
    -0.06
     Cuomo
    -0.06
    rawer
    -0.06
    ungs
    -0.06
    çĻ½æĿ¡
    -0.06
    ó
    -0.06
    POSITIVE LOGITS
    dap
    0.08
    <|fim_prefix|>
    0.07
    ัà¸ĩ
    0.07
    etype
    0.07
    à°¡à±į
    0.07
    à§įয
    0.07
    ÑĪÑĤе
    0.07
    çī¹æĸ¯
    0.07
     kino
    0.07
    社ä¼ļçļĦ
    0.07
    Activations Density 1.374%

    No Known Activations