© 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. 23113
    Prev
    Next
    INDEX
    Explanations

    structures become

    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
    éĴĪ对
    -0.07
    ivalent
    -0.07
    æĻ®åıĬ
    -0.06
    æ´ªæµģ
    -0.06
    çĻ¾å·Ŀ
    -0.06
     Levine
    -0.06
    .Emit
    -0.06
    éĴĪ对ä¸įåIJĮ
    -0.06
    mani
    -0.06
    stream
    -0.06
    POSITIVE LOGITS
    æĪIJç«ĭ以æĿ¥
    0.08
    好åij¢
    0.08
     formed
    0.08
    BaseContext
    0.08
    odon
    0.08
    sembl
    0.08
    éĿ¢ç§¯ä¸º
    0.08
    sembles
    0.08
    æĪIJç«ĭäºİ
    0.08
    eke
    0.08
    Activations Density 0.003%

    No Known Activations