© 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. 7144
    Prev
    Next
    INDEX
    Explanations

    illustrative document essay

    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
    -sort
    -0.07
    enser
    -0.07
    ç´§
    -0.07
    etik
    -0.07
    æĢ»æľīä¸Ģ天
    -0.07
    ued
    -0.07
    ÙĤس
    -0.07
     amongst
    -0.07
    ÑģÑĤи
    -0.07
    ì§ĢëıĦ
    -0.06
    POSITIVE LOGITS
    ysel
    0.08
    ç°¡
    0.07
    ä¸½å¨ľ
    0.07
    çļĭ
    0.06
    èĢĮçŁ¥
    0.06
    ä¸Ĭæĸĩ
    0.06
    ä¸ĭéĿ¢æĺ¯å°ıç¼ĸ
    0.06
    ä½°
    0.06
    ä¸ĭéĿ¢å°ıç¼ĸ
    0.06
    æĭīæĭī
    0.06
    Activations Density 0.007%

    No Known Activations