© 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. 44475
    Prev
    Next
    INDEX
    Explanations

    mathematical integrals and names

    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
    Negative Logits
    areth
    -0.09
    ienz
    -0.08
    ÑĢеменно
    -0.07
    åIJĦè¡ĮåIJĦ
    -0.07
    åĨįéĢł
    -0.07
    zah
    -0.07
    /bus
    -0.07
    teras
    -0.07
    actor
    -0.07
    entif
    -0.07
    POSITIVE LOGITS
    èµ·æŃ¢
    0.08
    积åĪĨ
    0.08
     between
    0.08
     endpoints
    0.08
     integral
    0.08
    between
    0.07
     междÑĥ
    0.07
    ç©įåĪĨ
    0.07
    ç¨
    0.07
     Between
    0.07
    Activations Density 0.004%

    No Known Activations