© 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. 23001
    Prev
    Next
    INDEX
    Explanations

    number of groups

    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
    cea
    -0.07
    cad
    -0.07
    å¤§åľ£
    -0.06
    uert
    -0.06
    Squared
    -0.06
    çļĦåĵģè´¨
    -0.06
    äºĨè¿ij
    -0.06
    awa
    -0.06
    ungg
    -0.06
    Merit
    -0.06
    POSITIVE LOGITS
     تعداد
    0.08
    plen
    0.08
    NumberOf
    0.08
    æľĢå°ij
    0.08
    æľĢå¤ļ
    0.08
    太å°ij
    0.07
     кÑĸлÑĮ
    0.07
    æĪĸå°ij
    0.07
    人æķ°çļĦ
    0.07
    à¸ŀà¸Ńà¸Ķี
    0.07
    Activations Density 0.004%

    No Known Activations