© 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. 49493
    Prev
    Next
    INDEX
    Explanations

    hydrogen

    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
    esy
    -0.07
    ä¸įå·®
    -0.07
    à¸ķิ
    -0.07
    zat
    -0.06
    æ¯Ļ
    -0.06
    abat
    -0.06
    imat
    -0.06
    红åı¶
    -0.06
    éľĨ
    -0.06
    balanced
    -0.06
    POSITIVE LOGITS
    бÑĢе
    0.09
    avian
    0.09
    à¹īาà¸ĩ
    0.08
    -major
    0.08
    æĪij为群ä¼ĹåĬŀå®ŀäºĭ
    0.08
    -rich
    0.08
    å¼ĢåĽ½
    0.08
    äºĨä¸ĭåİ»
    0.08
    raphics
    0.07
    æľ¬æĸĩéĵ¾æİ¥
    0.07
    Activations Density 0.004%

    No Known Activations