© 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. 47400
    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
    ãģĻãģ¿
    -0.08
    enal
    -0.07
    inkin
    -0.07
    hog
    -0.07
    äºijæ·¡
    -0.07
    à¸ŀิ
    -0.07
    Verifier
    -0.07
    æĸĩåĮĸåºķèķ´
    -0.06
     onLoad
    -0.06
    Singleton
    -0.06
    POSITIVE LOGITS
    äºĽè®¸
    0.08
    egu
    0.07
    eret
    0.07
    åıĹçļĦ
    0.07
    .argument
    0.07
    oseb
    0.07
    ие
    0.07
    ç°¿
    0.07
    sert
    0.07
    æĦŁæĥ³
    0.07
    Activations Density 0.000%

    No Known Activations