© 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. 35014
    Prev
    Next
    INDEX
    Explanations

    delete documents, plot code, jQuery procedure

    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
    instanc
    -0.07
    ×£
    -0.07
    <Response
    -0.07
    ysters
    -0.07
    èĬ
    -0.06
    ä¸įæĸĻ
    -0.06
    .ht
    -0.06
    ampur
    -0.06
    ondas
    -0.06
    ationer
    -0.06
    POSITIVE LOGITS
    ç»ļ
    0.07
    ãģ©ãģĵãĤį
    0.07
    gable
    0.07
     burge
    0.06
    身çļĦ
    0.06
    änden
    0.06
    تز
    0.06
    ded
    0.06
    =__
    0.06
    auses
    0.06
    Activations Density 0.312%

    No Known Activations