© 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. 29939
    Prev
    Next
    INDEX
    Explanations

    names with surnames

    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
    /out
    -0.07
    iliar
    -0.07
    aat
    -0.07
    ÑĢÑĥг
    -0.07
    /un
    -0.07
    ../
    -0.06
    zheimer
    -0.06
    çīĪæĿĥä¸İåħį责声æĺİ
    -0.06
    unta
    -0.06
    /down
    -0.06
    POSITIVE LOGITS
    angelo
    0.12
    sons
    0.11
    athan
    0.09
    ovich
    0.09
    iveness
    0.09
    stown
    0.08
     himself
    0.08
     ÐĺвановиÑĩ
    0.08
    icus
    0.08
    eux
    0.08
    Activations Density 1.140%

    No Known Activations