© 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. 11817
    Prev
    Next
    INDEX
    Explanations

    p-value significance

    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
    大å¼Ģ
    -0.09
    ÙĨاÙħ
    -0.08
    seau
    -0.08
    æĤ£
    -0.07
    -ID
    -0.07
    izzer
    -0.07
    åIJįæĢĿ
    -0.07
    两éĥ¨åĪĨ
    -0.06
     setSearch
    -0.06
    綾
    -0.06
    POSITIVE LOGITS
    çļĦç¨ĭ度
    0.08
    emper
    0.08
    tuig
    0.07
    æıIJ示信æģ¯
    0.07
    çĽ¸ä¼¼æĸĩçĮ®
    0.07
    次äºİ
    0.07
    ç´ļãģ®
    0.07
    级
    0.07
     accol
    0.07
    alker
    0.07
    Activations Density 0.008%

    No Known Activations