© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 37750
    Prev
    Next
    INDEX
    Explanations

    sales, box, inventory, object, card, demo

    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
    VERN
    -0.08
    ELLA
    -0.07
    ä¸įåĭķ
    -0.07
    orma
    -0.07
    otre
    -0.07
    ucci
    -0.07
     Peek
    -0.07
    idian
    -0.07
    éĶĢ
    -0.07
    ä¸įåĬ¨
    -0.07
    POSITIVE LOGITS
    oped
    0.08
    .arrow
    0.07
    nameof
    0.06
    Ïģικ
    0.06
     ev
    0.06
     Dentro
    0.06
    \_
    0.06
     Missile
    0.06
    å¸ĮæľĽä½łèĥ½
    0.06
     p
    0.06
    Activations Density 0.021%

    No Known Activations