© 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. 10477
    Prev
    Next
    INDEX
    Explanations

    medical or biological subjects

    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
     tang
    -0.07
    èħĬ
    -0.07
    boxed
    -0.06
    æĽĻ
    -0.06
    æı´
    -0.06
    èĩĺ
    -0.06
    ä¸įæĦģ
    -0.06
    kasten
    -0.06
     Tw
    -0.05
    ìĿĮ
    -0.05
    POSITIVE LOGITS
     ("<
    0.09
    otos
    0.08
    æ¯Ķå¦Ĥåľ¨
    0.08
    好åij¢
    0.08
    etos
    0.08
    å¦Ĥåľ¨
    0.08
    noch
    0.08
    —as
    0.08
     coquine
    0.08
    éĥijéĩį声æĺİ
    0.08
    Activations Density 0.242%

    No Known Activations