© 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. 43440
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and code punctuation

    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
    ä¸Ģå®ļéĩıçļĦ
    -0.07
     kern
    -0.07
    è´Ńä¹°åķĨåĵģ
    -0.07
    滨河
    -0.07
    èĩ´åĬĽäºİ为
    -0.07
    让广大
    -0.07
    æīİå®ŀåģļ好
    -0.06
    rokes
    -0.06
    tsy
    -0.06
    ethoven
    -0.06
    POSITIVE LOGITS
    解æĶ¾
    0.08
    éĢļ天
    0.07
    éĢļ
    0.07
    ju
    0.07
    ç¼ĵ
    0.07
    ÑģÑĥди
    0.07
    à¸Ľà¸£à¸°
    0.07
    ÙĬس
    0.07
    ongen
    0.07
    æIJŃ
    0.06
    Activations Density 0.007%

    No Known Activations