© 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. 58817
    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
    undra
    -0.09
    æĪ·
    -0.09
    fx
    -0.08
     repe
    -0.07
    æĪ·çļĦ
    -0.07
    ç¥Ŀç¦ıä½ł
    -0.07
    éĺ¿æĭī伯
    -0.07
    弯
    -0.06
    feh
    -0.06
    é¸ŃèĽĭ
    -0.06
    POSITIVE LOGITS
    å±ıé£İ
    0.09
    æĪª
    0.08
     intercepted
    0.08
    彪
    0.08
     juni
    0.07
     ethic
    0.07
    è¨ĵ
    0.07
    å¹´çļĦæŶåĢĻ
    0.07
    ntl
    0.07
    usic
    0.07
    Activations Density 0.000%

    No Known Activations