© 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. 37441
    Prev
    Next
    INDEX
    Explanations

    possessive names' creations or works

    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
    ansch
    -0.07
    çļĦåĨ³å®ļ
    -0.07
    *@
    -0.07
    çľĭæ¸ħæ¥ļ
    -0.06
    éĥ¨èIJ½å®¢
    -0.06
    fully
    -0.06
    çļĦåīįæıIJ
    -0.06
    кновен
    -0.06
    ä¸Ģå®ļçļĦ
    -0.06
    èĪ¬åľ°
    -0.06
    POSITIVE LOGITS
    éĥ½æľīåĵªäºĽ
    0.09
    ãģ¨è¨ĢãģĪãģ°
    0.09
    ãģ¨ãģĦãģĪãģ°
    0.09
    æľīåĵªäºĽ
    0.09
    诸
    0.08
    æľĢèijĹåIJįçļĦ
    0.08
    主è¦ģçļĦ
    0.08
     notable
    0.08
    izzi
    0.08
    社ä¼ļå®ŀ践活åĬ¨
    0.08
    Activations Density 0.064%

    No Known Activations