© 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. 65061
    Prev
    Next
    INDEX
    Explanations

    linked ads, heat lightning, super senior, flag weight, view of, direct-shift, refers to

    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
    VERR
    -0.08
    idel
    -0.08
    西çľģ
    -0.08
    inou
    -0.08
    çļĭ
    -0.08
    mares
    -0.08
    _SENT
    -0.07
    é£ŀå¿«
    -0.07
     Heidel
    -0.07
    enty
    -0.07
    POSITIVE LOGITS
    æĺ¯ä»Ģä¹ĪæĦıæĢĿ
    0.08
    çļĦæĦıæĢĿæĺ¯
    0.08
     refers
    0.08
    ãģ¨ãģĦãģĨè¨Ģèijī
    0.08
     meaning
    0.08
     بÙħعÙĨÙī
    0.07
    çļĦæĦıæĢĿ
    0.07
    ãģ¨ãģĦãģĨæĦıåij³
    0.07
    主è¦ģæĺ¯æĮĩ
    0.07
    æĮĩçļĦæĺ¯
    0.07
    Activations Density 0.027%

    No Known Activations