© 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. 58485
    Prev
    Next
    INDEX
    Explanations

    JSON structure delimiters

    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
    eg
    -0.06
    è¦ģä¸į
    -0.06
    pot
    -0.06
    strup
    -0.06
    ardon
    -0.06
    严éĩįæŶ
    -0.06
    è¯Ľ
    -0.06
    _argument
    -0.06
    第ä¸Ģè´¢ç»ı
    -0.06
    ollywood
    -0.06
    POSITIVE LOGITS
    ×ĺ×Ļ×Ŀ
    0.07
    hte
    0.07
    Ø·ÙĨ
    0.07
    _ln
    0.07
    avent
    0.07
    utre
    0.07
    uttle
    0.07
    tricos
    0.07
    ItemId
    0.07
    atakan
    0.07
    Activations Density 0.013%

    No Known Activations