© 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. 41315
    Prev
    Next
    INDEX
    Explanations

    gospel and faith teachings

    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¸įèī¯å½±åĵį
    -0.07
     CONTRIBUTORS
    -0.07
     undesirable
    -0.07
     hÆ°á»Łng
    -0.06
    大æīĵ
    -0.06
     ê¸į
    -0.06
     upscale
    -0.06
    åį°è±¡
    -0.06
     Fant
    -0.06
    æĬ¢çľ¼
    -0.06
    POSITIVE LOGITS
    羣çIJĨ
    0.10
    æł¸å¿ĥçļĦ
    0.09
    çļĦæł¸å¿ĥ
    0.09
    è¿Ļå¥Ĺ
    0.09
     truths
    0.09
     core
    0.09
    æł¸å¿ĥ
    0.09
    宣讲
    0.09
    æĺ¯ä¸Ģå¥Ĺ
    0.09
    ç£Ĭ
    0.08
    Activations Density 0.064%

    No Known Activations