© 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. 7188
    Prev
    Next
    INDEX
    Explanations

    unless or until

    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
    ä¸įä¹ı
    -0.08
     wherever
    -0.08
    èĤ¡ä¸ľä¿¡æģ¯
    -0.07
     jopa
    -0.07
    å§Ķåijĺä¼ļå§Ķåijĺ
    -0.07
    çĶļèĩ³è¿ĺæľī
    -0.07
    nock
    -0.07
    _checker
    -0.07
    itzt
    -0.07
    tanto
    -0.07
    POSITIVE LOGITS
    æīįè¡Į
    0.17
     somehow
    0.12
    æīįåı¯ä»¥
    0.11
    åIJ¦åĪĻ
    0.11
    æīįæľīåı¯èĥ½
    0.10
    æīįä¼ļ
    0.10
    æīįåı¯
    0.10
    æĺİç¡®
    0.09
     explicitly
    0.09
     explicit
    0.09
    Activations Density 0.137%

    No Known Activations