© 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. 7511
    Prev
    Next
    INDEX
    Explanations

    accompanied with

    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
    insky
    -0.08
    åĩºæģ¯
    -0.07
    боÑĢÑĭ
    -0.07
    æĬĢæľ¯ä¸Ĭ
    -0.07
    ä¹ĥ
    -0.07
    ourcem
    -0.07
    áĢķáĢº
    -0.07
    atti
    -0.07
     nanti
    -0.07
     tecnic
    -0.07
    POSITIVE LOGITS
     outweigh
    0.08
    تا
    0.07
    wan
    0.07
    主è¦ģä½ĵçİ°åľ¨
    0.06
    缺失
    0.06
    illard
    0.06
    å¦Ĥ对
    0.06
    ä½ĵçİ°åľ¨
    0.06
    åĴĮä¿¡æģ¯åĮĸ
    0.06
    è¿ĻäºĽåĽłç´ł
    0.06
    Activations Density 0.622%

    No Known Activations