© 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. 55041
    Prev
    Next
    INDEX
    Explanations

    what is the

    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
    Negative Logits
    æ½ľç§»é»ĺ
    -0.08
    [loc
    -0.08
    <dd
    -0.08
    inkel
    -0.08
    —for
    -0.08
    —they
    -0.08
    ä½Ĩä¸įéĻIJäºİ
    -0.08
    efon
    -0.08
    åľ¨åģļ好
    -0.07
    æĢ§ä»·
    -0.07
    POSITIVE LOGITS
    çľģ
    0.07
    çľģçķ¥
    0.07
    ç¥
    0.07
    åıİ
    0.07
    æ¨
    0.07
    k
    0.06
    身
    0.06
    æİ¥è¿ij
    0.06
    æĶ¶
    0.06
    奴
    0.06
    Activations Density 0.117%

    No Known Activations