© 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. 44520
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ¬ģ
    -0.08
    ä¸įå¿ħè¦ģçļĦ
    -0.07
    _macros
    -0.07
    ä¸Ģå®ļ
    -0.07
    å¾Īå°ij
    -0.07
    essler
    -0.07
     Garner
    -0.07
    主ãģª
    -0.07
    .crt
    -0.07
    eneric
    -0.06
    POSITIVE LOGITS
    à®Łà®¿à®¯
    0.08
    æ·±æľī
    0.07
    endor
    0.07
    kan
    0.07
    ythe
    0.07
     brod
    0.07
    åĤ¬äºº
    0.07
    -append
    0.07
     ÑĥÑģÑĤав
    0.06
    ä¹Łæĺ¯åįģåĪĨ
    0.06
    Activations Density 0.000%

    No Known Activations