© 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. 4571
    Prev
    Next
    INDEX
    Explanations

    programming language keywords

    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
    ä½Ĩä¸įæĺ¯
    -0.07
    ä½Ĩ没æľī
    -0.07
    archy
    -0.06
    æľ¬æĬ¥
    -0.06
    ials
    -0.06
    erei
    -0.06
    uchs
    -0.06
    ore
    -0.06
    没æľīä¸Ŀ毫
    -0.06
    /about
    -0.06
    POSITIVE LOGITS
    ÂŃing
    0.09
    åħ¬ç½ijå®īå¤ĩ
    0.09
    idora
    0.07
    ÂŃs
    0.07
    á»ijc
    0.07
    aná
    0.07
    ÂŃt
    0.07
    toh
    0.07
     CONCAT
    0.07
     ÂŃ
    0.07
    Activations Density 2.130%

    No Known Activations