© 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. 33674
    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
    çļ¿
    -0.09
    roz
    -0.08
    ÙĪÙĨØ©
    -0.07
     Testament
    -0.07
    oden
    -0.07
    ound
    -0.07
    uton
    -0.07
    ä¼ļå±ķä¸Ńå¿ĥ
    -0.07
    icar
    -0.07
    ithe
    -0.07
    POSITIVE LOGITS
    æĢ»åĪĨ
    0.07
     sest
    0.07
    æŁĦ
    0.06
    åŃ
    0.06
    åıĺéĩı
    0.06
    mys
    0.06
    è¿Ľåĩºåı£
    0.06
     fre
    0.06
    oland
    0.06
    -mult
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.