© 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. 54910
    Prev
    Next
    INDEX
    Explanations

    list initialization with commas

    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
    欣
    -0.08
    uit
    -0.08
    ä¼ijçľł
    -0.07
    åİ»ä½ķ
    -0.07
    /upload
    -0.07
    zer
    -0.07
     prop
    -0.07
     Hanson
    -0.06
    å¢Ł
    -0.06
    rix
    -0.06
    POSITIVE LOGITS
    phis
    0.09
    olda
    0.08
    ĥģ
    0.08
    illard
    0.07
     geïn
    0.07
    询价
    0.07
    xEB
    0.07
    xBC
    0.07
    è·¯éĢı
    0.07
     ÐijÑĥдÑĥ
    0.07
    Activations Density 0.026%

    No Known Activations