© 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. 11271
    Prev
    Next
    INDEX
    Explanations

    clot formation, qualifying matches, prenatal, perfusion

    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
    ä¸ºæł¸å¿ĥçļĦåħļä¸Ń央
    -0.07
    åħħåĪĨè°ĥåĬ¨
    -0.07
    emiz
    -0.06
    escu
    -0.06
    пÑĢавка
    -0.06
    rup
    -0.06
    _unref
    -0.06
    ./.
    -0.06
     USAGE
    -0.06
    łĢ
    -0.06
    POSITIVE LOGITS
    çĦ¶åIJİæĺ¯
    0.11
    åħĪæĿ¥
    0.10
     followed
    0.09
     ìĭľìŀijìľ¼ë¡ľ
    0.09
    åħĪè¡Į
    0.09
     먼ìłĢ
    0.09
     puis
    0.09
     seguida
    0.09
    åħĪçľĭ
    0.08
    åħĪåľ¨
    0.08
    Activations Density 0.526%

    No Known Activations