© 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. 48531
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    æĺ±
    -0.07
    æĬĢæľ¯ä¸Ĭ
    -0.07
    éľĢçĶ¨
    -0.07
    æĹłæļĩ
    -0.07
     minus
    -0.06
    esu
    -0.06
    å¥Īä½ķ
    -0.06
    ([-
    -0.06
    说起æĿ¥
    -0.06
    ä¸įåĴĮ
    -0.06
    POSITIVE LOGITS
    å¤ļ彩çļĦ
    0.07
     affian
    0.07
    ķ
    0.07
    ysi
    0.07
    Ïģα
    0.06
    haltens
    0.06
     Heck
    0.06
    å¤ļæł·çļĦ
    0.06
    ئة
    0.06
    porto
    0.06
    Activations Density 0.000%

    No Known Activations