© 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. 46103
    Prev
    Next
    INDEX
    Explanations

    code syntax elements

    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
     devidamente
    -0.07
    amik
    -0.07
    /feed
    -0.07
    umbu
    -0.07
    crement
    -0.07
    inia
    -0.07
    ÙħÙĬ
    -0.07
     érd
    -0.06
     getHeight
    -0.06
    _fre
    -0.06
    POSITIVE LOGITS
     Dieter
    0.07
    ä¸Ģ空
    0.06
    ç¨ĭ度çļĦ
    0.06
    æĥħ人
    0.06
    æīĵåİĭ
    0.06
     nullable
    0.06
    oso
    0.06
    ard
    0.06
     scouting
    0.06
     Parall
    0.06
    Activations Density 0.004%

    No Known Activations