© 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. 52041
    Prev
    Next
    INDEX
    Explanations

    collectively, individually, groups, matrices, functions

    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
    åĩ¡äºĭ
    -0.07
    è¿Ļé¢Ĺ
    -0.07
     midway
    -0.07
     halfway
    -0.06
    arkin
    -0.06
    ä¸Ĭåīį
    -0.06
    两æĸ¹éĿ¢
    -0.06
    æĺĨ
    -0.06
    æĿľ
    -0.06
    eliz
    -0.06
    POSITIVE LOGITS
    åIJĦèĩªçļĦ
    0.13
    å½¼æѤ
    0.12
    å½¼æѤçļĦ
    0.12
    åIJĦèĩª
    0.11
    åIJĦæľīåIJĦ
    0.10
     collectively
    0.10
     themselves
    0.10
    约èĢĮåIJĮ
    0.10
    ãģĿãĤĮãģŀãĤĮ
    0.10
     individually
    0.10
    Activations Density 0.067%

    No Known Activations