© 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. 23202
    Prev
    Next
    INDEX
    Explanations

    matrix notation, lists of numbers

    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
    åIJİæīįèĥ½
    -0.08
     Reinh
    -0.08
    çİĭ建
    -0.07
    acular
    -0.07
    agli
    -0.07
    iful
    -0.07
    æĽ´åºĶ该
    -0.06
    reis
    -0.06
    .Must
    -0.06
    大éĸĢ
    -0.06
    POSITIVE LOGITS
    ppy
    0.08
    说ä¸įåĩºçļĦ
    0.08
    æ±²
    0.08
    ÑĤей
    0.07
    èļģ
    0.07
    æ»ļæ»ļ
    0.07
    åıª
    0.07
    sche
    0.07
    perc
    0.07
    çĻ¾äºº
    0.07
    Activations Density 0.009%

    No Known Activations