© 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. 60083
    Prev
    Next
    INDEX
    Explanations

    exhibiting characteristics

    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
    vier
    -0.08
    abric
    -0.07
    æŀĦ建åĴĮè°IJ
    -0.07
    ç«ĭå¾·
    -0.07
    æ·±çŁ¥
    -0.07
    öh
    -0.07
    ç´§è¦ģ
    -0.07
    ë©Ģ
    -0.07
    fabric
    -0.07
    建档ç«ĭåį¡
    -0.07
    POSITIVE LOGITS
    æĢİæł·çļĦ
    0.09
    ä¸įåIJĮç¨ĭ度çļĦ
    0.09
     ÑĤенден
    0.08
    ä¸Ĭåįĩè¶ĭåĬ¿
    0.08
     signs
    0.08
    è¿Ļç§įè¡Į为
    0.08
     пÑĢизнаки
    0.08
     behavior
    0.08
    ively
    0.08
    antly
    0.08
    Activations Density 0.135%

    No Known Activations