© 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. 35043
    Prev
    Next
    INDEX
    Explanations

    keywords, notes, or introductory phrases

    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
    ä¸ĭåIJĮ
    -0.08
    quential
    -0.08
    affaire
    -0.07
    odash
    -0.07
    ughs
    -0.07
    appy
    -0.07
    åĽŀäºĭ
    -0.07
    /of
    -0.07
    å°Ķå¤ļ
    -0.07
    .getError
    -0.07
    POSITIVE LOGITS
    ä¸įåIJĮçļĦæĺ¯
    0.08
    åĢ¼å¾Ĺ注æĦıçļĦæĺ¯
    0.08
    éľĢè¦ģ注æĦıçļĦæĺ¯
    0.08
     importantly
    0.07
    åĢ¼å¾Ĺä¸ĢæıIJçļĦæĺ¯
    0.07
    注
    0.07
     NOTE
    0.07
    éģĹæĨ¾çļĦæĺ¯
    0.07
    NOTE
    0.07
    è¿ĻäºĽéĥ½
    0.07
    Activations Density 0.016%

    No Known Activations