© 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. 808
    Prev
    Next
    INDEX
    Explanations

    phrases starting with specific topics/names

    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
    åĽ¾ä¸º
    -0.09
    ä½łæĺ¯æĪij
    -0.06
    çĪ±æĺ¯
    -0.06
    enca
    -0.06
     Äijáo
    -0.06
    ׳×Ļ×Ķ
    -0.06
    æł¼æĸ¯
    -0.06
    ä½łæĺ¯æĪijçļĦ
    -0.06
    adore
    -0.06
    orous
    -0.06
    POSITIVE LOGITS
    人æĿ¥è¯´
    0.19
    èĢĮè¨Ģ
    0.18
    æĿ¥è¯´
    0.17
    çļĦ人æĿ¥è¯´
    0.17
    ä¾Ĩ說
    0.14
    æĥħåĨµæĿ¥çľĭ
    0.12
    æĪijæĿ¥è¯´
    0.12
     ÙģØ¥ÙĨÙĩ
    0.11
    æĸ¹éĿ¢çļĦéĹ®é¢ĺ
    0.11
    ãģĭãģ¨ãģĦãģĨãģ¨
    0.11
    Activations Density 0.080%

    No Known Activations