© 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. 818
    Prev
    Next
    INDEX
    Explanations

    multi-module maven

    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
    æľĢä½³çļĦ
    -0.07
     hoz
    -0.07
    红èī²çļĦ
    -0.07
    stel
    -0.07
    ÑĦÑĦ
    -0.06
    ond
    -0.06
    éģ¨æ¸¸
    -0.06
     inz
    -0.06
    ç²īèī²çļĦ
    -0.06
    ngh
    -0.06
    POSITIVE LOGITS
    ominated
    0.08
    å¤§æľ¬èIJ¥
    0.08
    lient
    0.07
    rophe
    0.07
    aeda
    0.07
    è°ģæĺ¯
    0.07
    ç¿
    0.07
    çļĦä¸ĸçķĮéĩĮ
    0.07
    parated
    0.07
     Shea
    0.07
    Activations Density 0.177%

    No Known Activations