© 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. 34936
    Prev
    Next
    INDEX
    Explanations

    a statute, familiar, typical

    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
    åĽ¾æºIJ
    -0.08
    ä¸īéĿ¢
    -0.07
    делÑĮ
    -0.07
    غر
    -0.07
     ($.
    -0.07
    ENSOR
    -0.07
    æĶ»åŁİ
    -0.07
    éĵ¶è¡ĮèĤ¡ä»½æľīéĻIJåħ¬åı¸
    -0.07
    arat
    -0.07
    kowski
    -0.07
    POSITIVE LOGITS
    é¢ĺå¹²
    0.08
    åľ¨ä»ĬåIJİçļĦå·¥ä½ľä¸Ń
    0.08
    µ
    0.07
    å¡«åħ¥
    0.07
    idos
    0.07
    urre
    0.06
    主è¦ģè´Łè´£
    0.06
    inkin
    0.06
    鼨çļĦ
    0.06
     primary
    0.06
    Activations Density 0.004%

    No Known Activations