© 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. 38137
    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
    aza
    -0.07
     (...)
    -0.06
    uth
    -0.06
    åĭī强
    -0.06
    åľ¨åħ¶ä¸Ń
    -0.06
    azar
    -0.06
    ird
    -0.06
    ä¸īçŃī
    -0.06
    è°ĭ
    -0.06
    stin
    -0.06
    POSITIVE LOGITS
    ulier
    0.08
    á»ĵn
    0.08
    åģ¥åħ¨çļĦ
    0.07
    å®Ĺ主
    0.07
    èŀŁ
    0.07
    è¹ĭ
    0.07
    acct
    0.07
    åıĸåĨ³
    0.07
    à¹Īวัà¸Ļ
    0.07
    unen
    0.07
    Activations Density 0.000%

    No Known Activations