© 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. 55172
    Prev
    Next
    INDEX
    Explanations

    negative impacts or quantities

    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
    zor
    -0.07
    ç¡®æľī
    -0.07
    åħ¨
    -0.07
     ÐľÐµÐ´
    -0.07
    reif
    -0.07
    èī¯
    -0.07
    å·¥ç¨ĭéĻ¢
    -0.07
    å¾Ĺ人
    -0.07
    [__
    -0.07
     صدا
    -0.07
    POSITIVE LOGITS
    ãģĹãģ¾ãģĨãģ¨
    0.07
    ç¼¥
    0.07
    ãģĹãģŁåł´åIJĪ
    0.07
    æľªåıĬæŶ
    0.07
    è¿Ļæł·çļĦè¯Ŀ
    0.07
    æĪĸæľª
    0.07
    impl
    0.07
    -than
    0.07
    è¿Ļæł·ä¸Ģç§į
    0.06
    дав
    0.06
    Activations Density 0.029%

    No Known Activations