© 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. 51872
    Prev
    Next
    INDEX
    Explanations

    .sql file or private key

    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
    inh
    -0.09
    kof
    -0.08
    æľīå¥ĸ
    -0.08
     Aleg
    -0.07
    ska
    -0.07
    jemu
    -0.07
    ofd
    -0.07
    eguard
    -0.07
    ylim
    -0.07
    inus
    -0.07
    POSITIVE LOGITS
    åķĬ
    0.07
     tadi
    0.07
    æ§
    0.07
    æĿ¥èĩª
    0.07
    å½¹
    0.06
    éĿ¢å¯¹
    0.06
    天éķ¿
    0.06
    æ³
    0.06
    rado
    0.06
    èĬ¹
    0.06
    Activations Density 0.006%

    No Known Activations