© 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. 34504
    Prev
    Next
    INDEX
    Explanations

    tables and code | delimiters

    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
    ostar
    -0.07
    åĸ±
    -0.07
    ä¸Ģåħ±
    -0.07
    èĭ±æĸĩåIJįåŃĹ
    -0.07
    æľĢåIJİä¸Ģåħ¬éĩĮ
    -0.07
    æīĵæŃ»
    -0.06
    uyan
    -0.06
    èµ°åIJ§
    -0.06
    hopefully
    -0.06
    ä¸įå¾Ĺ以任ä½ķ
    -0.06
    POSITIVE LOGITS
    emn
    0.07
    obra
    0.07
    esk
    0.07
    adh
    0.07
    åºŀ
    0.07
    ä¼ļæīĢ
    0.07
    æľīä½Ļ
    0.07
    enj
    0.07
    _From
    0.07
    ç»Ļèĩªå·±çļĦ
    0.07
    Activations Density 0.002%

    No Known Activations