© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 23523
    Prev
    Next
    INDEX
    Explanations

    user ID or pid

    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
    å¹´é¾Ħåľ¨
    -0.08
    ä¸Ģå¸Ĩ
    -0.07
    scan
    -0.07
    å¥ļ
    -0.07
    ä¸įå°ijäºİ
    -0.07
    åıĹäºĨ
    -0.07
    èĩ³å°ijåľ¨
    -0.07
     berusia
    -0.07
     âg
    -0.07
     atleast
    -0.07
    POSITIVE LOGITS
    æ¯Ķ
    0.07
    solo
    0.07
    erja
    0.07
    æ²½
    0.07
    çķ¥å¾®
    0.07
    ancode
    0.07
    _RESOLUTION
    0.06
    enca
    0.06
    ontan
    0.06
     solo
    0.06
    Activations Density 0.090%

    No Known Activations