© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 34783
    Prev
    Next
    INDEX
    Explanations

    medical contexts and professional terminology

    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
    _BEFORE
    -0.06
    æĬ«
    -0.06
    oule
    -0.06
    æ¯ı天æĹ©ä¸Ĭ
    -0.06
    ä¸İç¾İåĽ½
    -0.06
    ãĥ¡ãĥª
    -0.06
     aute
    -0.06
    æĺ¯æ°´
    -0.06
    æĪ´çĿĢ
    -0.06
    éħ¬
    -0.06
    POSITIVE LOGITS
    åĥıä½ł
    0.10
    æľ¬æ¡Ī
    0.09
    ä¸ĬéĿ¢çļĦ
    0.09
    å¦Ĥä¸Ĭ
    0.08
    æģ©æĸ¯
    0.08
    åĥı
    0.08
    转载请注æĺİåĩºå¤Ħ
    0.08
    hoff
    0.07
    ä¸ĬéĿ¢
    0.07
    èĬĤåºĨ
    0.07
    Activations Density 0.270%

    No Known Activations