© 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. 58119
    Prev
    Next
    INDEX
    Explanations

    future strategies and applications

    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
    è¿Ļåı«
    -0.07
    iak
    -0.07
    umus
    -0.07
     usually
    -0.07
    çĭ¬ä¸ĢæĹł
    -0.06
    æ¯Ķä½ł
    -0.06
    utherland
    -0.06
    fang
    -0.06
    å¹²åĺĽ
    -0.06
    ç»´ä¹Łçº³
    -0.06
    POSITIVE LOGITS
    ä¸įä¹ħçļĦå°ĨæĿ¥
    0.10
    ä»ĬåIJİ
    0.10
     future
    0.09
    åľ¨æľªæĿ¥çļĦ
    0.09
    åľ¨ä»ĬåIJİçļĦ
    0.09
     someday
    0.08
    future
    0.08
    åľ¨ä»ĬåIJİ
    0.08
    æĹ©æĹ¥
    0.08
     forthcoming
    0.08
    Activations Density 1.271%

    No Known Activations