© 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. 45619
    Prev
    Next
    INDEX
    Explanations

    . chapter citation

    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
    说ä¸įå®ļ
    -0.07
    logger
    -0.07
    ierge
    -0.07
     möglicherweise
    -0.07
    union
    -0.07
    èĢĮä¸Ķä¹Ł
    -0.07
    tn
    -0.07
    ling
    -0.07
    æīĢå±ŀ
    -0.07
    èĢĮä¸Ķè¿ĺæľī
    -0.07
    POSITIVE LOGITS
    araus
    0.08
    å¼ķåĩº
    0.08
    å¼ķçĶ³
    0.08
    æĻ®
    0.07
    æĻ®éģįçļĦ
    0.07
    çĶ±æѤ
    0.07
    ç»ĵæŀľè¡¨æĺİ
    0.07
     daÃŃ
    0.07
    éĢļè¿ĩ对
    0.07
    uhl
    0.07
    Activations Density 0.003%

    No Known Activations