© 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. 37481
    Prev
    Next
    INDEX
    Explanations

    home runs, assists, runs, games played

    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
     log
    -0.06
     anomal
    -0.06
    æĥĬéŃĤ
    -0.06
     pressure
    -0.06
    åĮ¿åIJį
    -0.06
     Hutchinson
    -0.06
    çŃ
    -0.06
    åİĭåĬĽ
    -0.06
     Rum
    -0.05
    å°Ķæĸ¯
    -0.05
    POSITIVE LOGITS
    à¹Ģหล
    0.09
    ç«ĭåį³ä¸ĭè½½
    0.09
    [table
    0.08
    éĩį大æĦıä¹ī
    0.08
    à¸ŀัà¸Ļà¸ĺà¹Į
    0.08
    sted
    0.07
     IMPORTANT
    0.07
    ainties
    0.07
    ArrayType
    0.07
    ixo
    0.07
    Activations Density 0.013%

    No Known Activations