© 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. 49838
    Prev
    Next
    INDEX
    Explanations

    association between exposure to preoperative diabetes

    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
    åĪ·åĪ·
    -0.07
    recision
    -0.07
     Williamson
    -0.07
     pär
    -0.06
    rafa
    -0.06
    bah
    -0.06
    roid
    -0.06
    ('.',
    -0.06
    ulk
    -0.06
    濯
    -0.06
    POSITIVE LOGITS
     hypo
    0.09
     exposure
    0.08
    æļ´éľ²
    0.08
     Zut
    0.08
     ÑıкобÑĭ
    0.08
    åĽłæŀľ
    0.08
     hypothesis
    0.08
    æĪĸåħ¶
    0.08
    åIJĦ级åħļå§Ķ
    0.07
     Exposure
    0.07
    Activations Density 0.203%

    No Known Activations