© 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. 44767
    Prev
    Next
    INDEX
    Explanations

    number constants or punctuation

    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
    ä¸ĢåĽŀäºĭ
    -0.07
    çĤĻ
    -0.07
    δά
    -0.07
    oppen
    -0.06
    é»ĦéħĴ
    -0.06
    ç¥ŀåħ½
    -0.06
    jen
    -0.06
    Hub
    -0.06
    éļı
    -0.06
    ç¼ĵ
    -0.06
    POSITIVE LOGITS
    ibert
    0.08
    umbu
    0.08
    .nodeType
    0.08
    uclear
    0.07
    æĿİäºij
    0.07
    sink
    0.07
    ydd
    0.07
    icated
    0.07
    atric
    0.07
    'aut
    0.07
    Activations Density 0.004%

    No Known Activations