© 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. 60232
    Prev
    Next
    INDEX
    Explanations

    bug fixes and updates

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     Zob
    -0.09
    类似çļĦ
    -0.08
    ÏĨÏĮ
    -0.08
    å¾Īå¿«å°±
    -0.08
    nowrap
    -0.08
    DAQ
    -0.08
    Eventually
    -0.07
     eventual
    -0.07
    usak
    -0.07
     ultimately
    -0.07
    POSITIVE LOGITS
     new
    0.11
    æĸ°ãģŁãģ«
    0.10
    æĸ°çļĦ
    0.10
     новÑĭÑħ
    0.09
    æĸ°å¢ŀäºĨ
    0.09
    æĸ°å¢ŀ
    0.09
    æľīæĸ°çļĦ
    0.08
     новÑĭм
    0.08
    ä¹ŁæĽ´åĬł
    0.08
     neue
    0.08
    Activations Density 0.192%

    No Known Activations