© 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. 34024
    Prev
    Next
    INDEX
    Explanations

    Sufism, Zen, Shia, Neo-Confucianism

    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¸ŃæĸĩçīĪ
    -0.07
    rani
    -0.07
    lng
    -0.06
    éħĭ
    -0.06
    åIJĦè¡ĮåIJĦ
    -0.06
     Trib
    -0.06
     trib
    -0.06
    azer
    -0.06
    åĴĮèĥ½åĬĽ
    -0.06
    åħ¬æ°ij
    -0.06
    POSITIVE LOGITS
    åĪĨæĶ¯
    0.08
    odox
    0.08
     lineage
    0.08
    é¼İ缼
    0.08
     revival
    0.08
    æŃ£ç»Ł
    0.08
    ä¸Ģæ´¾
    0.08
    çļĦä¼łæĴŃ
    0.08
     doctrines
    0.08
    路线
    0.08
    Activations Density 0.020%

    No Known Activations