© 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. 9833
    Prev
    Next
    INDEX
    Explanations

    first name then last name

    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
    æĽ´ä¸Ĭä¸Ģå±Ĥ楼
    -0.06
    æīĢ说çļĦ
    -0.06
    æĽ´åĬłçļĦ
    -0.06
    夥
    -0.06
     fort
    -0.06
    èĬ¸
    -0.06
    æīĢ使çĶ¨çļĦ
    -0.06
     faster
    -0.05
     simply
    -0.05
    '
    -0.05
    POSITIVE LOGITS
    ?,?,?,?,
    0.11
    lifi
    0.08
    ozilla
    0.08
    acan
    0.08
    ','','
    0.08
    ãĢįãĢĮ
    0.08
    agung
    0.08
    å®Ŀå¡Ķ
    0.08
    neh
    0.08
    ","","
    0.07
    Activations Density 0.074%

    No Known Activations