© 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. 25726
    Prev
    Next
    INDEX
    Explanations

    code snippets with programming terms

    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
    é»Ħé¾Ļ
    -0.06
    eon
    -0.06
    ä¸įå¿ĺ
    -0.06
    赶紧æĿ¥
    -0.06
    DOG
    -0.06
    вов
    -0.06
    ä¹Ķ丹
    -0.06
    jure
    -0.06
     etc
    -0.06
    .TypeOf
    -0.06
    POSITIVE LOGITS
    éĺħè¯»æľ¬æĸĩåīį
    0.09
    缴æİ¥æĪĸéĹ´æİ¥
    0.08
     kulinar
    0.08
    ystore
    0.08
     eksk
    0.08
    åĴĮæľªæĿ¥
    0.08
    ä¸ĢåĽ¢
    0.08
    æľ¬æĸĩ为åįļ主
    0.08
     tille
    0.08
    Kamis
    0.07
    Activations Density 0.003%

    No Known Activations