© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 8339
    Prev
    Next
    INDEX
    Explanations

    people dead or wounded

    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
    ä¸įå·®
    -0.07
     Rac
    -0.07
    äºĮä½į
    -0.07
     imprim
    -0.07
    à¸Ńà¸ģ
    -0.06
    ç§ijåijĺ
    -0.06
    ä¾įéĥİ
    -0.06
     strstr
    -0.06
    æłĩçļĦ
    -0.06
    æݨèįIJç»Ļ
    -0.06
    POSITIVE LOGITS
    æĢ»æķ°
    0.10
    人æķ°
    0.10
    à¸Īำà¸Ļวà¸Ļมาà¸ģ
    0.09
    主è¦ģæĿ¥èĩª
    0.09
    æķ°éĩı
    0.09
    åħ¶ä¸ŃåĮħæĭ¬
    0.08
    à¸Īำà¸Ļวà¸Ļ
    0.08
    çļĦæķ°éĩı
    0.08
    人æķ¸
    0.08
     outnumber
    0.08
    Activations Density 0.208%

    No Known Activations