© 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. 12184
    Prev
    Next
    INDEX
    Explanations

    software updates and patches

    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
    -output
    -0.08
    åIJijåħļ
    -0.07
     inout
    -0.07
     WTF
    -0.07
    汽车ç½ij
    -0.07
    ç½ijç«Ļé¦ĸ页
    -0.07
    åħħåĪĨè°ĥåĬ¨
    -0.07
    à¸Łà¸·à¹īà¸Ļ
    -0.07
    Startup
    -0.07
    /tty
    -0.07
    POSITIVE LOGITS
     updates
    0.14
    Updates
    0.12
    æĽ´æĸ°
    0.12
    æĽ´æĸ°çļĦ
    0.11
     update
    0.11
     обновлениÑı
    0.11
     Updates
    0.11
    updates
    0.11
     version
    0.11
     upgrades
    0.10
    Activations Density 0.226%

    No Known Activations