© 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. 29255
    Prev
    Next
    INDEX
    Explanations

    good or satisfactory

    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
     poorly
    -0.09
    æŁIJäºĽ
    -0.09
    æŁIJä¸Ģ天
    -0.09
    ä¸įå®Įåħ¨
    -0.09
    æŁIJç§į
    -0.09
     somewhat
    -0.09
    ä¸į太好
    -0.09
    ãģĵãģ¨ãģĮãģĤãĤĭ
    -0.09
    ä¸įä¸Ģå®ļ
    -0.09
     gotta
    -0.08
    POSITIVE LOGITS
    没æľīéĹ®é¢ĺ
    0.13
    ä¸įä¼ļåĩºçİ°
    0.12
    没æľīåĩºçİ°
    0.12
    ä¸įä¼ļåĽłä¸º
    0.12
    åı¯ä»¥æĶ¾å¿ĥ
    0.10
    没æľīä¸Ŀ毫
    0.10
    ç»ıå¾Ĺèµ·
    0.10
     satisfactory
    0.10
    ä¸įçĶ¨æĭħå¿ĥ
    0.09
     âľĶ
    0.09
    Activations Density 0.081%

    No Known Activations