© 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. 32932
    Prev
    Next
    INDEX
    Explanations

    top of, area nationwide, during a, early moments, parts of, entire application

    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¤ķ
    -0.09
    ussin
    -0.08
    avax
    -0.08
    serter
    -0.08
    åĨ²å¤©
    -0.08
    anova
    -0.08
    ÑĢио
    -0.08
    sass
    -0.08
    renom
    -0.08
    æĽ¾çĶ¨åIJį
    -0.08
    POSITIVE LOGITS
     world
    0.08
    world
    0.08
    åľ°çIJĥ
    0.07
    åħ¨çIJĥ
    0.07
     society
    0.07
    æĪijåĽ½
    0.07
    çļĦä¸ĸçķĮ
    0.07
     our
    0.07
    ä¸ĸçķĮ
    0.07
    çݰ代社ä¼ļ
    0.07
    Activations Density 1.885%

    No Known Activations