© 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. 47004
    Prev
    Next
    INDEX
    Explanations

    supervised training, ologic studies, XML

    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
    åıĬåIJĦ
    -0.07
    åıĬæľīåħ³
    -0.07
    åıĬ缸åħ³
    -0.06
    วà¸Ļ
    -0.06
    æĹĹä¸ĭçļĦ
    -0.06
    ικ
    -0.06
     Sheldon
    -0.06
    åĴĮåIJĦ
    -0.06
    åĴĮæĪij们
    -0.06
    Dear
    -0.06
    POSITIVE LOGITS
     elsewhere
    0.08
    ä¸į该
    0.08
    mage
    0.08
     everywhere
    0.08
    orton
    0.08
    stellen
    0.07
    ãĤ³ãĥ¼ãĥĪ
    0.07
    è¾¹çķĮ
    0.07
    æ¥
    0.07
    rying
    0.07
    Activations Density 0.003%

    No Known Activations