© 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. 10237
    Prev
    Next
    INDEX
    Explanations

    Buddhism and Buddhist concepts

    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
     patriot
    -0.08
    é»į
    -0.08
    天çĦ¶æ°Ķ
    -0.07
    swagger
    -0.07
    bour
    -0.07
    ê·
    -0.07
     mex
    -0.07
    çħ¤æ°Ķ
    -0.07
    lope
    -0.07
    misc
    -0.06
    POSITIVE LOGITS
     Buddhist
    0.14
     Buddhism
    0.13
    æĪIJä½Ľ
    0.12
    èĪ¬èĭ¥
    0.12
    æħĪæĤ²
    0.11
     Buddha
    0.11
    æ¸ħåĩĢ
    0.11
    寺éĻ¢
    0.11
     Buddh
    0.11
    梵
    0.11
    Activations Density 0.060%

    No Known Activations