© 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. 45120
    Prev
    Next
    INDEX
    Explanations

    German words like `Untersuch`, `erset`, `Allein unter Bauern`, `Maschinen Krieger`, `Lebenslauf`

    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
    çݯèĬĤä¸Ń
    -0.08
    çļĦæĹ¥åŃIJéĩĮ
    -0.08
     succesfully
    -0.07
     seperate
    -0.07
    arda
    -0.07
    代表çĿĢ
    -0.07
    èĮĥæĸĩç½ij
    -0.06
    ç´§å¼łçļĦ
    -0.06
    -non
    -0.06
    راÙĤÙĬ
    -0.06
    POSITIVE LOGITS
    æıIJæIJº
    0.08
    é»ij马
    0.07
    èĢģå°Ĩ
    0.07
    ÑĢÑİ
    0.07
     addCriterion
    0.07
    æ¢
    0.07
     '{@
    0.07
    æĻ¤
    0.07
    驻马
    0.07
    erset
    0.07
    Activations Density 0.038%

    No Known Activations