© 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. 8947
    Prev
    Next
    INDEX
    Explanations

    births

    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
    å°¼äºļ
    -0.07
    ç«ĭåį³ä¸ĭè½½
    -0.07
    emie
    -0.06
    溪åİ¿
    -0.06
    æķĻèĤ²ç½ij
    -0.06
    ½ij
    -0.06
    ız
    -0.06
    çļĦå¿ĥä¸Ń
    -0.06
    å¸¸åľ¨
    -0.06
    ç«ĭä¿¡
    -0.06
    POSITIVE LOGITS
    ³
    0.08
    -utils
    0.07
    SEE
    0.07
    undert
    0.07
    addock
    0.07
    ç§ijåѦåĮĸ
    0.07
    Ø·ÙĦ
    0.07
    æĭ¼
    0.07
     demise
    0.06
    ูล
    0.06
    Activations Density 0.036%

    No Known Activations