© 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. 798
    Prev
    Next
    INDEX
    Explanations

    km²

    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
    <|box_end|>
    -0.11
    ़
    -0.11
    quiera
    -0.09
    ëĭ¤ë©´
    -0.09
    à¸ģารà¸ĵà¹Į
    -0.09
    æł·çļĦ
    -0.09
    ignment
    -0.08
    ation
    -0.08
    ìļĶ
    -0.08
    åħ¼æĢ»ç»ıçIJĨ
    -0.08
    POSITIVE LOGITS
    s
    0.15
    ãĥ³
    0.15
    ãģĦãĤĭ
    0.12
    ات
    0.12
    о
    0.12
    ë¡ľ
    0.12
    o
    0.12
    zelfde
    0.10
    ×Ļ×Ŀ
    0.10
    ر
    0.09
    Activations Density 0.002%

    No Known Activations