© 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. 55240
    Prev
    Next
    INDEX
    Explanations

    danger or ER or successful

    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
    Not in Any Lists

    No Comments

    Negative Logits
    Sus
    -0.08
     Sus
    -0.08
    sus
    -0.07
    è¿Ļ对äºİ
    -0.06
    ä¸ĢèĪ¬
    -0.06
    å¤ļæĸ¹éĿ¢
    -0.06
    æѦå¨ģ
    -0.06
    èµ
    -0.06
     exclusive
    -0.06
    acco
    -0.06
    POSITIVE LOGITS
    ä¸įæĺ¯åĽłä¸º
    0.17
    ä¸įæĺ¯ä¸ºäºĨ
    0.16
    ä¸įåľ¨äºİ
    0.14
    ä¸įæĺ¯åľ¨
    0.14
    ä¸įæĺ¯è¯´
    0.14
    ä¸įåıªæĺ¯
    0.14
    并éĿŀæĺ¯
    0.13
     bukan
    0.13
    çļĦä¸įæĺ¯
    0.13
    ä»ĸä¸įæĺ¯
    0.13
    Activations Density 0.061%

    No Known Activations