© 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. 39171
    Prev
    Next
    INDEX
    Explanations

    fusion and plasma physics research

    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
    è·ĭ
    -0.08
     tread
    -0.07
    èĪĹ
    -0.07
    caffe
    -0.07
    åĴĸåķ¡
    -0.07
     Lug
    -0.06
    个æ¡Ī
    -0.06
    éĴ¢çIJ´
    -0.06
    ÑģкÑĢÑĭ
    -0.06
    é£Ĵ
    -0.06
    POSITIVE LOGITS
     helium
    0.09
    诱
    0.08
    çļĦé«ĺ温
    0.08
    åĬªåĬĽå®ŀçİ°
    0.08
    çĤ¹çģ«
    0.08
     physics
    0.08
    模æĭŁ
    0.08
    apons
    0.08
     churras
    0.07
     simulations
    0.07
    Activations Density 0.059%

    No Known Activations