© 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. 44499
    Prev
    Next
    INDEX
    Explanations

    request, policy, provided, method

    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
    轻轻æĿ¾
    -0.09
    åºĶæĢ¥ç®¡çIJĨå±Ģ
    -0.08
    æ¯Ķä¸Ĭå¹´å¢ŀéķ¿
    -0.07
    èµĦ产交æĺĵ
    -0.07
    ç»ıèIJ¥èĮĥåĽ´åĮħæĭ¬
    -0.07
    ä¸ŃåĽ½åĮº
    -0.07
    åĩĢåĪ©
    -0.07
    æĽ´å¥½çļĦèĩªå·±
    -0.07
    æ¯ķä¸ļçĶŁå°±ä¸ļ
    -0.07
    åѦéĻ¢éĻ¢éķ¿
    -0.07
    POSITIVE LOGITS
     respective
    0.09
    æĮīçħ§
    0.08
    ä¸¥æł¼æĮīçħ§
    0.08
    ä¾Ŀçħ§
    0.08
    åIJĮæŃ¥
    0.08
     entirety
    0.08
    æĹłä»»ä½ķ
    0.08
     firstly
    0.08
     presently
    0.08
    æĺ¯æĮīçħ§
    0.08
    Activations Density 0.056%

    No Known Activations