© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 11872
    Prev
    Next
    INDEX
    Explanations

    reports, tablets, malls, advertise, printing, furnished

    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
    AllWindows
    -0.07
    人åĵģ
    -0.07
    estä
    -0.07
    spflicht
    -0.07
    GRES
    -0.07
    sweise
    -0.07
     coloni
    -0.07
    çĥģ
    -0.07
    кÑĥÑĢо
    -0.07
    gres
    -0.06
    POSITIVE LOGITS
    øy
    0.09
    imon
    0.06
    auen
    0.06
    ×ķ×Ļ
    0.06
    uai
    0.06
    ieten
    0.06
    /
    0.06
    utti
    0.06
    ish
    0.06
    -hooks
    0.06
    Activations Density 0.054%

    No Known Activations