© 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. 51955
    Prev
    Next
    INDEX
    Explanations

    /bin/env scripts

    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
    Ñģлан
    -0.09
    imed
    -0.09
    ulkan
    -0.09
    umas
    -0.08
    ATAB
    -0.08
    ajer
    -0.08
    èĿī
    -0.08
    гÑĢаÑĦи
    -0.08
    anse
    -0.08
    hein
    -0.08
    POSITIVE LOGITS
    éļ
    0.07
    æ¹ĸéĩĮ
    0.07
    ms
    0.06
    vista
    0.06
    .or
    0.06
    hawk
    0.06
    ze
    0.06
    .github
    0.06
    Ø
    0.06
    ä
    0.06
    Activations Density 0.001%

    No Known Activations