© 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. 55061
    Prev
    Next
    INDEX
    Explanations

    after certain numbers

    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
    大è¿IJ
    -0.07
    çļĦæ¯ıä¸Ģ
    -0.06
    å¹»æĥ³
    -0.06
    arro
    -0.06
    cente
    -0.06
    æħµ
    -0.06
    aturi
    -0.06
    ç´§çĽ¯
    -0.06
    вÑĪи
    -0.06
    Feder
    -0.06
    POSITIVE LOGITS
    è¿Ļç§įçݰ象
    0.08
    hum
    0.07
    ÄĥÈĽ
    0.07
    å°½æľī
    0.07
     hum
    0.07
    åĽłä¸ºè¿ĻäºĽ
    0.07
    è¿Ļç§įåģļæ³ķ
    0.07
    atel
    0.07
    à¤łà¤¾
    0.07
    æĹłæģĻ
    0.07
    Activations Density 0.601%

    No Known Activations