© 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. 33374
    Prev
    Next
    INDEX
    Explanations

    numerals and names

    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
    ugin
    -0.08
     Wig
    -0.07
    æŀĦæĪIJçĬ¯ç½ªçļĦ
    -0.07
    į
    -0.07
    éĹ´
    -0.07
    æłij人
    -0.07
    æħķå°¼
    -0.07
    ulte
    -0.07
    озна
    -0.07
    å¾ģ
    -0.07
    POSITIVE LOGITS
    æĺİæĹ¥
    0.07
    åIJĮä¸Ĭ
    0.07
     Imper
    0.07
     react
    0.06
    IBC
    0.06
    ORM
    0.06
    wat
    0.06
    ä»įæľª
    0.06
    éªij
    0.06
     taj
    0.06
    Activations Density 0.143%

    No Known Activations