© 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. 40089
    Prev
    Next
    INDEX
    Explanations

    medical/surgical/pediatric oncology unit workflows

    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¸įèĥ½å¤Ł
    -0.09
    èĥ½å¤ŁæľīæķĪ
    -0.09
    æĽ´åĬłçļĦ
    -0.09
    并ä¸Ķè¿ĺ
    -0.08
    æĤ¨æīĢ
    -0.08
    éĥ½èĥ½å¤Ł
    -0.08
    èĥ½å¤ŁæĽ´å¥½åľ°
    -0.08
     altogether
    -0.08
    å¹´çļĦæŶåĢĻ
    -0.08
    æĪĸèĢħ说
    -0.08
    POSITIVE LOGITS
    ìĹIJìĦł
    0.09
    ìĹĶ
    0.08
     Dù
    0.08
     meski
    0.08
    两ç§įæĸ¹å¼ı
    0.08
     dziÅĽ
    0.08
    å¢ŀèĩ³
    0.08
     dibanding
    0.08
    麦åŃIJ
    0.07
    èĭ¥éĿŀ
    0.07
    Activations Density 0.003%

    No Known Activations