© 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. 34762
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ires
    -0.07
    ://${
    -0.06
    jet
    -0.06
    ä¹ĭéģĵ
    -0.06
    fy
    -0.06
    ":[{"
    -0.06
    вно
    -0.06
    åݿ人æ°ijåĮ»éĻ¢
    -0.06
    ://{
    -0.06
    ®
    -0.06
    POSITIVE LOGITS
    oenix
    0.08
    enan
    0.08
    iscard
    0.08
    å¾·ç½Ĺ
    0.07
    ordion
    0.07
    ä¸įå®ĮçļĦ
    0.07
    instanc
    0.07
    _inp
    0.07
    tesi
    0.07
    roup
    0.07
    Activations Density 0.003%

    No Known Activations