© 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. 34987
    Prev
    Next
    INDEX
    Explanations

    miliary, ice, losses, excluded, expected, list

    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
    âĢ¦),
    -0.08
    andone
    -0.07
    æīĢåij¨
    -0.07
    ä¸ĭè¿°
    -0.07
    ä¸ĭéĿ¢æĺ¯å°ıç¼ĸ
    -0.07
    ä¸įä¼ij
    -0.07
    çŃīè¿Ľè¡Į
    -0.07
    å¦Ĥåħ¶
    -0.07
    ä¸ĭéĿ¢å°±
    -0.07
    è¿ĺæľīå°±æĺ¯
    -0.07
    POSITIVE LOGITS
    ä¹Łå°±ä¸į
    0.09
    !!!!!!!!
    0.07
    //@
    0.07
    ovah
    0.07
    rowse
    0.06
    æİĸ
    0.06
    ropolis
    0.06
    äºĨåIJĹ
    0.06
     !!!
    0.06
    åŁĭæĢ¨
    0.06
    Activations Density 0.006%

    No Known Activations