© 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. 46144
    Prev
    Next
    INDEX
    Explanations

    then followed by a verb

    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
    缮åīįå·²ç»ı
    -0.09
    ier
    -0.08
     nowadays
    -0.08
    çİ°åľ¨å·²ç»ı
    -0.08
    对åħ¶çľŁå®ŀæĢ§è´Łè´£
    -0.08
     finora
    -0.08
    èĩ³ä»Ĭ
    -0.07
    çİ°åľ¨æĺ¯
    -0.07
    à¸ĵ
    -0.07
    intang
    -0.07
    POSITIVE LOGITS
    adays
    0.10
    æĪIJ为ä¸Ģç§į
    0.08
    èĢĮæĿ¥çļĦ
    0.08
    mehr
    0.07
    èĢĮä¸Ķä¹Ł
    0.07
    åĴĮæľªæĿ¥
    0.07
    çĶ±åİŁåijĬ
    0.07
    ledes
    0.07
    çĿĢæĪijçļĦ
    0.07
    ç¼¥
    0.07
    Activations Density 0.064%

    No Known Activations