© 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. 4281
    Prev
    Next
    INDEX
    Explanations

    regulation and feedback

    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
    害
    -0.07
    á»ı
    -0.07
    fel
    -0.07
     rá»Ŀi
    -0.07
     sạch
    -0.07
    ETT
    -0.07
    embe
    -0.07
    ä¸įæĥĬ
    -0.07
     trag
    -0.07
    iddles
    -0.07
    POSITIVE LOGITS
     corrective
    0.12
    è°ĥèĬĤ
    0.11
     automatically
    0.10
    èĩªåĬ¨
    0.10
     feedback
    0.10
    feedback
    0.09
    平衡
    0.09
     Feedback
    0.09
    Feedback
    0.09
     balancing
    0.09
    Activations Density 0.091%

    No Known Activations