© 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. 28438
    Prev
    Next
    INDEX
    Explanations

    film festival debut

    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
    vere
    -0.07
    orta
    -0.07
    çĶ¨æĪ·æıIJä¾Ľ
    -0.07
    VER
    -0.07
    veren
    -0.07
    volo
    -0.07
    versed
    -0.07
    /span
    -0.07
    פק
    -0.07
    ä¸ŃæĹ¥
    -0.06
    POSITIVE LOGITS
    ãĤĤãģ®ãģĮ
    0.07
    åĨµ
    0.07
    åĴĮå¿«ä¹IJ
    0.07
    é¡¹çĽ®åľ¨
    0.07
    ä¹Łåı¯ä»¥åľ¨
    0.07
    è¦ģ被
    0.07
    reed
    0.07
    计åĪĴåľ¨
    0.06
    åİħ
    0.06
    人被
    0.06
    Activations Density 0.318%

    No Known Activations