© 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. 44885
    Prev
    Next
    INDEX
    Explanations

    partition function

    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
    _limits
    -0.07
    çļĦæľ¬
    -0.07
    ä¼´
    -0.07
     ÑĥкÑĥ
    -0.07
    rou
    -0.07
     Sched
    -0.06
    dec
    -0.06
    Register
    -0.06
    èĪį
    -0.06
    æĿ¯ä¸Ń
    -0.06
    POSITIVE LOGITS
     homm
    0.08
    好æĸĩ
    0.08
    oui
    0.07
    ustus
    0.07
    .realpath
    0.07
    weis
    0.07
    ombat
    0.07
    æľĢåIJİä¸Ģ天
    0.06
    panies
    0.06
    oud
    0.06
    Activations Density 0.003%

    No Known Activations