© 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. 4633
    Prev
    Next
    INDEX
    Explanations

    my code

    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
    ä¸Ĭå¸ĤåIJİ
    -0.09
    åłªèĥ½
    -0.07
    _finalize
    -0.07
    subpackage
    -0.07
    ély
    -0.07
    BOOT
    -0.07
    åIJĮ类产åĵģ
    -0.07
    æľĢåIJİåľ¨
    -0.07
    å±ĢéĻIJ
    -0.07
    åIJİæľŁçļĦ
    -0.07
    POSITIVE LOGITS
     before
    0.08
     оÑĩеÑĢед
    0.08
     оÑĩеÑĢедной
    0.07
    æĸ°çļĦä¸Ģ
    0.07
     önce
    0.06
    åķĨ
    0.06
    ë§Īëĭ¤
    0.06
     Progr
    0.06
    before
    0.06
     trÆ°á»Ľc
    0.06
    Activations Density 0.041%

    No Known Activations