© 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. 7012
    Prev
    Next
    INDEX
    Explanations

    study and revision materials

    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
     approving
    -0.08
    idere
    -0.07
    .ravel
    -0.07
    ç³Ļ
    -0.07
    让人们
    -0.07
    让对æĸ¹
    -0.07
    åIJĮå·¥
    -0.07
    å©´åĦ¿
    -0.07
    åĮ»ç§ij大åѦéĻĦå±ŀ
    -0.07
     primitive
    -0.07
    POSITIVE LOGITS
     cram
    0.11
    åIJĦç§ij
    0.09
    åĪ»èĭ¦
    0.09
    æŁ¥æ¼ı补缺
    0.09
    çªģåĩ»
    0.09
    åŃ¦ä¹łä¹łæĥ¯
    0.09
    åĨ²åĪº
    0.09
    æĶ»åħĭ
    0.08
    æľīæķĪæıIJåįĩ
    0.08
    å¤ĩèĢĥ
    0.08
    Activations Density 0.073%

    No Known Activations