© 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. 26083
    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
    acap
    -0.08
    utori
    -0.08
    ס×Ļ×Ŀ
    -0.08
    overs
    -0.08
    建设æĬķèµĦ
    -0.08
    å®ĮæĪIJæĬķèµĦ
    -0.07
    utes
    -0.07
    å¤ĸéĥ¨çݯå¢ĥ
    -0.07
    engi
    -0.07
    nze
    -0.07
    POSITIVE LOGITS
    æĿı
    0.07
    linux
    0.07
    immat
    0.06
     "../../../../
    0.06
    ificado
    0.06
    inox
    0.06
    akil
    0.06
    Args
    0.06
    èĴ¸èĴ¸
    0.06
    ä¸įæĶ¾
    0.06
    Activations Density 0.000%

    No Known Activations