© 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. 7251
    Prev
    Next
    INDEX
    Explanations

    code snippets, programming context

    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
    è¤
    -0.07
    çģ¿
    -0.07
    à¹īา
    -0.06
    æĪijåIJĥ
    -0.06
    人æĦı
    -0.06
     Hassan
    -0.06
    æĺ
    -0.06
    away
    -0.06
    帮åĬ©çļĦ人
    -0.06
     banker
    -0.06
    POSITIVE LOGITS
    æŶæ¯ı
    0.09
    çĪ±ä¸į
    0.08
    enor
    0.07
    ãĤ¥
    0.07
    PathComponent
    0.07
    auft
    0.07
    ä¿ŀ
    0.07
    à¹Īย
    0.07
    éĻª
    0.07
    THR
    0.07
    Activations Density 0.003%

    No Known Activations