© 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. 44291
    Prev
    Next
    INDEX
    Explanations

    end of

    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
    azi
    -0.06
     sou
    -0.06
    æľĶ
    -0.06
    ubo
    -0.06
    pera
    -0.06
     hamm
    -0.06
    erner
    -0.06
    èĶĵ
    -0.06
    enga
    -0.06
    ekh
    -0.06
    POSITIVE LOGITS
    oral
    0.08
    ãĤĦãģ¤
    0.08
    é»ŀçļĦ
    0.08
    à¸ŀุà¸ĺ
    0.07
    ãģ¨ãģĹãģ¦ãģ®
    0.07
    ä¸įåIJĮç±»åŀĭçļĦ
    0.07
    inken
    0.07
    åķĨæłĩä¿¡æģ¯
    0.07
    ialized
    0.07
     cantar
    0.07
    Activations Density 1.520%

    No Known Activations