© 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. 13319
    Prev
    Next
    INDEX
    Explanations

    numbered lists and mathematical symbols

    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
    åĿŀ
    -0.08
     Cano
    -0.07
    ä¸ĩä¸ĩ
    -0.07
    arn
    -0.07
    é¾Ļçİĭ
    -0.07
     Bid
    -0.07
     proc
    -0.06
     lá»įt
    -0.06
    prog
    -0.06
    bid
    -0.06
    POSITIVE LOGITS
    åĻ¨çŃī
    0.08
    orius
    0.07
    xFFF
    0.07
    群çļĦ
    0.07
    群人
    0.07
    è¿Ļ两ç§į
    0.07
    emonic
    0.07
    tras
    0.07
    ipper
    0.07
    onal
    0.07
    Activations Density 0.004%

    No Known Activations