© 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. 44481
    Prev
    Next
    INDEX
    Explanations

    logging and debugging output

    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
    ersch
    -0.09
    -INF
    -0.08
    _OVERRIDE
    -0.07
    éĩijèŀįæľįåĬ¡
    -0.07
    ÅĽc
    -0.07
    ç»Ļ对æĸ¹
    -0.07
    羣æĺ¯ä¸ª
    -0.07
    骨èĤī
    -0.07
    (today
    -0.07
    buster
    -0.07
    POSITIVE LOGITS
    ound
    0.07
     dbg
    0.07
    _debug
    0.07
     getLogger
    0.07
    GER
    0.07
    .debug
    0.07
    /debug
    0.07
     DBG
    0.07
    æīĢ称
    0.07
    .Debug
    0.06
    Activations Density 0.039%

    No Known Activations