© 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. 9482
    Prev
    Next
    INDEX
    Explanations

    medical procedures

    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
    æģĴå®ļ
    -0.08
     Comunicazione
    -0.06
    veau
    -0.06
    åģ¥åħ¨çļĦ
    -0.06
    æ±Ĥæķij
    -0.06
    æĿ¥æºIJäºİç½ij绾
    -0.06
     communicating
    -0.06
    åģ¥åħ¨
    -0.06
    çĬ¶åĨµ
    -0.06
    åĪļåĪ°
    -0.06
    POSITIVE LOGITS
    ä¸ĢæĿ¡é¾Ļ
    0.09
     performed
    0.09
    verfahren
    0.09
    æĪIJåĬŁçļĦ
    0.08
    ÛĮات
    0.08
    æľ¯
    0.08
    ä¸Ģ次
    0.08
     followed
    0.08
     procedure
    0.08
    æīĵæĸŃ
    0.08
    Activations Density 0.598%

    No Known Activations