© 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. 13607
    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
    麼
    -0.07
    æľĿ天
    -0.07
     either
    -0.07
     **.**
    -0.07
     appunto
    -0.06
     whatever
    -0.06
    ungg
    -0.06
    *;
    -0.06
     whichever
    -0.06
     либо
    -0.05
    POSITIVE LOGITS
    çīĪæĿĥä¸İåħį责声æĺİ
    0.09
    åĢ¼å¾Ĺä¸ĢæıIJ
    0.08
    åĨħ容ä¸İ
    0.07
     ÙħÙħÙĨ
    0.07
    说åĪ°è¿ĻéĩĮ
    0.07
    æī©å±ķèµĦæĸĻ
    0.07
    交æµģä¸İ
    0.07
    å¤ļæݪ并举
    0.07
    (vo
    0.07
    è¿Ľä¸ĢæŃ¥å¼ºåĮĸ
    0.07
    Activations Density 0.000%

    No Known Activations