© 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. 12339
    Prev
    Next
    INDEX
    Explanations

    mathematical variables and symbols

    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
    çħ²
    -0.07
    ney
    -0.07
    otto
    -0.07
    责任å¿ĥ强
    -0.07
    ijt
    -0.07
    æħ¢
    -0.07
    nsk
    -0.07
    èĩªæĭħ
    -0.06
     günstig
    -0.06
    ä¿Ŀåħ¨
    -0.06
    POSITIVE LOGITS
    æľĿ天
    0.07
    cini
    0.07
    ä¸ĩéĩĮ
    0.07
    æ»´æ°´
    0.07
    emaker
    0.07
    reh
    0.07
     dius
    0.06
    交éĢļ
    0.06
    ourg
    0.06
    ilater
    0.06
    Activations Density 0.035%

    No Known Activations