© 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. 8605
    Prev
    Next
    INDEX
    Explanations

    trade and competition

    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
    ogie
    -0.06
    éĢı
    -0.06
    æijĺèĩª
    -0.06
    ett
    -0.06
    Qualified
    -0.06
    inka
    -0.06
    æĥħ
    -0.06
    读èĢħ
    -0.06
    SCRIPT
    -0.06
    opter
    -0.06
    POSITIVE LOGITS
    mate
    0.07
    碩
    0.07
    mates
    0.07
    joj
    0.07
    ä¹ĭä¸į
    0.07
     подÑĩи
    0.06
    ologne
    0.06
    ç¡ķ
    0.06
    registro
    0.06
    letcher
    0.06
    Activations Density 0.001%

    No Known Activations