© 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. 18057
    Prev
    Next
    INDEX
    Explanations

    python imports

    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
    wards
    -0.07
    olut
    -0.07
    ention
    -0.07
     Sorg
    -0.07
    yc
    -0.07
    _decision
    -0.07
    upported
    -0.07
     подÑĬ
    -0.07
    ornado
    -0.07
    éĺħ读åħ¨æĸĩ
    -0.07
    POSITIVE LOGITS
    yth
    0.07
    ä¸įå®ļ
    0.07
    rita
    0.07
    æ·Ĩ
    0.06
    adesh
    0.06
    /licenses
    0.06
    rous
    0.06
    çļĦå°ıæīĭ
    0.06
    iori
    0.06
    ogramm
    0.06
    Activations Density 0.005%

    No Known Activations