© 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. 37914
    Prev
    Next
    INDEX
    Explanations

    medical and scientific 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
    anju
    -0.08
    åºĶå°½éĩı
    -0.07
    æ¯Ķçħ§
    -0.07
    options
    -0.07
    bies
    -0.06
    缮ä¸Ń
    -0.06
    åĴĮæݨ广
    -0.06
     Ease
    -0.06
    è¿Ķ
    -0.06
    ä¸į符åIJĪ
    -0.06
    POSITIVE LOGITS
    -driven
    0.12
    为ä¾Ŀæīĺ
    0.11
    çļĦä½ľçĶ¨ä¸ĭ
    0.10
    æĺ¯åħ³éĶ®
    0.10
    驱åĬ¨çļĦ
    0.10
    çļĦæĶ¯æĮģä¸ĭ
    0.10
    -based
    0.09
    -mediated
    0.09
    驱åĬ¨
    0.09
    ä½ľçĶ¨ä¸ĭ
    0.09
    Activations Density 0.143%

    No Known Activations