© 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. 37770
    Prev
    Next
    INDEX
    Explanations

    is a

    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
     ëĤĺìĦľ
    -0.08
    ளà¯įள
    -0.08
    fern
    -0.07
    ãģĦãģıãģ¤ãģĭ
    -0.07
    æĹłå¼Ĥ
    -0.07
    认为æĺ¯
    -0.07
     resembling
    -0.07
    æĽ´å¤ļçļĦ
    -0.07
     ìĿ´ëĬĶ
    -0.07
    iveness
    -0.07
    POSITIVE LOGITS
    åĽŀäºĭ
    0.11
     Bestandteil
    0.10
     geweest
    0.10
    ffect
    0.09
    ä¸įéĶĻçļĦéĢīæĭ©
    0.09
    ä¸ĢåĽŀäºĭ
    0.09
    åIJįåī¯åħ¶å®ŀçļĦ
    0.09
    à¹Ħà¸Ľà¸ķาม
    0.08
     gì
    0.08
    çļĦéĩįè¦ģç»ĦæĪIJéĥ¨åĪĨ
    0.08
    Activations Density 0.311%

    No Known Activations