© 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. 42925
    Prev
    Next
    INDEX
    Explanations

    medical field

    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
    éģ½
    -0.08
    æ¯ıä¸Ģç§į
    -0.07
    å¦Ĩ
    -0.07
    å¦ĸåŃ½
    -0.07
    rechn
    -0.07
    好å¿ĥæĥħ
    -0.07
    temp
    -0.07
    UTT
    -0.07
    æľįåĬ¡è´¹
    -0.07
    ayang
    -0.07
    POSITIVE LOGITS
    ä¸Ģæł·
    0.08
    åIJĮ级
    0.07
    åIJĮçŃī
    0.07
    ä¹ĭå¤Ħåľ¨äºİ
    0.07
    ä¸įåIJĮçļĦæĺ¯
    0.07
    åIJĮåı°
    0.07
    åIJĮå·¥
    0.07
    0.07
    åIJĮæľŁ
    0.07
     counterparts
    0.07
    Activations Density 0.192%

    No Known Activations