© 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. 58893
    Prev
    Next
    INDEX
    Explanations

    precedential or non-precedential

    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
    emble
    -0.08
    iset
    -0.08
    æݺ
    -0.08
    ôi
    -0.08
    격
    -0.07
    pire
    -0.07
     lẽ
    -0.06
    _RENDERER
    -0.06
    éĽĨåĽ¢åľ¨
    -0.06
    éķĩçļĦ
    -0.06
    POSITIVE LOGITS
    è¿ĺæĺ¯
    0.13
    æĬijæĪĸ
    0.11
    éĤĦæĺ¯
    0.11
    è¿ĺæĺ¯ä¸į
    0.11
    è¿ĺæĺ¯æľī
    0.10
    è¿ĺæĺ¯åľ¨
    0.10
    è¿ĺæĺ¯éľĢè¦ģ
    0.09
    äºĨåIJĹ
    0.09
    è¿ĺæĺ¯åı¯ä»¥
    0.08
    è¿ĺæĺ¯ä»¥
    0.08
    Activations Density 0.038%

    No Known Activations