© 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. 803
    Prev
    Next
    INDEX
    Explanations

    each followed by a distinct item

    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
    æĺ¯ä¸Ģ缴
    -0.08
    atted
    -0.08
    æĹłäºº
    -0.07
    两大
    -0.07
    çļĦ两个
    -0.07
    èĩ³äºİ
    -0.07
    æķ´ä½ĵä¸Ĭ
    -0.07
    iam
    -0.07
    两çĶ¨
    -0.07
    jem
    -0.07
    POSITIVE LOGITS
    æľīä¸įåIJĮçļĦ
    0.11
    éĥ½æľīåħ¶
    0.10
    éĥ½æľīä¸įåIJĮçļĦ
    0.10
    éĥ½æľīèĩªå·±çļĦ
    0.10
    æľīèĩªå·±çļĦ
    0.09
    ë§Īëĭ¤
    0.09
    ä¸įåIJĮçļĦ
    0.09
    ä¸įåIJĮç±»åŀĭ
    0.08
    åIJĦæľī
    0.08
    ä¸įåIJĮç±»åŀĭçļĦ
    0.08
    Activations Density 0.104%

    No Known Activations