© 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. 26589
    Prev
    Next
    INDEX
    Explanations

    circuit elements and methods

    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
    rovers
    -0.07
    Cpp
    -0.07
    uren
    -0.07
    urvey
    -0.07
     Cesare
    -0.07
     Dani
    -0.07
    ç§ijçļĦ
    -0.07
    uro
    -0.07
    PRS
    -0.07
    ardon
    -0.07
    POSITIVE LOGITS
    inte
    0.07
    irman
    0.07
    ÑĢам
    0.07
    æĸĩæijĺ
    0.07
    ieke
    0.07
     unnamed
    0.07
    Ùĩد
    0.07
     vô
    0.06
     Rim
    0.06
    vid
    0.06
    Activations Density 0.570%

    No Known Activations