© 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. 37585
    Prev
    Next
    INDEX
    Explanations

    levels increased significantly

    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
    licit
    -0.07
    æĢ
    -0.07
    æ³ĵ
    -0.06
    伦
    -0.06
    aps
    -0.06
    bai
    -0.06
    ismet
    -0.06
    èij
    -0.06
     Provincial
    -0.06
    ux
    -0.06
    POSITIVE LOGITS
    åľ¨ä¸¤
    0.08
    è¿Ļæĸ¹éĿ¢
    0.08
    aur
    0.08
    头çŃī
    0.07
    ầu
    0.07
    è°ĥæŁ¥æĺ¾ç¤º
    0.07
    两èĢħçļĦ
    0.07
    paru
    0.07
    /Web
    0.07
    Ĥ
    0.07
    Activations Density 0.044%

    No Known Activations