© 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. 25085
    Prev
    Next
    INDEX
    Explanations

    among them

    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
    åIJĮä¸Ĭ
    -0.08
    æķ´ä¸ª
    -0.07
     вÑģей
    -0.07
    äºĨæķ´ä¸ª
    -0.07
    æķ´ä¸ªäºº
    -0.07
    åħ¨æĸĩ
    -0.07
    igor
    -0.07
    whole
    -0.07
     whole
    -0.07
    ä¸ĢåĪĩçļĦ
    -0.07
    POSITIVE LOGITS
    ä¸Ģ个æĺ¯
    0.13
    ä¸įä¹ı
    0.10
    ä¸Ģç§įæĺ¯
    0.10
    佼佼èĢħ
    0.10
     ones
    0.10
     íķĺëĤĺëĬĶ
    0.09
    åĵªä¸Ģ个
    0.09
    åĵªäºĽ
    0.09
    大éĥ¨åĪĨéĥ½æĺ¯
    0.09
     biri
    0.08
    Activations Density 0.086%

    No Known Activations