© 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. 49832
    Prev
    Next
    INDEX
    Explanations

    court of appeals

    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
    walt
    -0.08
    erce
    -0.08
    åľ©
    -0.08
    wad
    -0.08
    ä¸įåĢĴ
    -0.07
    idios
    -0.07
    ugno
    -0.07
    adb
    -0.07
    ovas
    -0.07
    ackers
    -0.07
    POSITIVE LOGITS
    nt
    0.07
    à¤Ĺà¥Ģ
    0.06
    etter
    0.06
    be
    0.06
     Lar
    0.06
    zier
    0.06
    è´Ŀ
    0.06
    доб
    0.06
    dan
    0.06
    æĥŁæľī
    0.06
    Activations Density 0.001%

    No Known Activations