© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 47874
    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
    Not in Any Lists

    No Comments

    Negative Logits
    äºĨ解èĩªå·±çļĦ
    -0.07
    åĽ½éŨ
    -0.07
    Invoker
    -0.07
    ä¿Ŀè¯ģ
    -0.07
    ä¸įåĪĨ
    -0.07
     hog
    -0.06
    çŃĶæ¡Ī解æŀIJ
    -0.06
    æĶ¿åºľåľ¨
    -0.06
    onga
    -0.06
    ä¿ĿæĬ¤èĩªå·±
    -0.06
    POSITIVE LOGITS
     additional
    0.08
    é¢Ŀå¤ĸ
    0.08
    bruck
    0.07
    additional
    0.07
    éļ¨æĻĤ
    0.07
     ÙħÙĨØŃ
    0.07
    arts
    0.07
    .additional
    0.07
     дополниÑĤелÑĮ
    0.07
    Å¡tÄĽ
    0.07
    Activations Density 0.000%

    No Known Activations