© 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. 50898
    Prev
    Next
    INDEX
    Explanations

    æĪªåĽ¾, charging, storytelling, plumbing

    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
    veen
    -0.09
    åıijå±ķçļĦéľĢè¦ģ
    -0.08
    edException
    -0.08
    ÅĤod
    -0.08
    ighted
    -0.08
    miet
    -0.08
    çļĦ带é¢Ĩä¸ĭ
    -0.08
    ized
    -0.08
    erven
    -0.07
    ipper
    -0.07
    POSITIVE LOGITS
    è¿ĩç¨ĭä¸Ń
    0.09
    æĸ¹å¼ı
    0.08
    äºİ人
    0.08
    ame
    0.08
    åĻ¨çļĦ
    0.08
    èĢħ为
    0.08
    åIJİçļĦ
    0.08
    ä¸İåIJ¦
    0.07
    æĸ¹å¼ı为
    0.07
    ÑĢе
    0.07
    Activations Density 0.016%

    No Known Activations