© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 20308
    Prev
    Next
    INDEX
    Explanations

    when followed by a noun

    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
    initely
    -0.09
    جاÙħ
    -0.08
    igger
    -0.07
    éķ¿åĬ¿
    -0.07
    ibly
    -0.07
    ãģķãģ¾
    -0.07
    丸
    -0.07
    elo
    -0.07
    æīĢ
    -0.07
    èı
    -0.07
    POSITIVE LOGITS
    满å¿ĥ
    0.07
    主é¢ĺ为
    0.07
     XXL
    0.07
    尺寸为
    0.06
    (Source
    0.06
    æ¯Ķä»ĸ
    0.06
    æ¯Ķèĩªå·±
    0.06
    é¢ĺ为
    0.06
    æĪijåĽ½çļĦ
    0.06
    ä¹ĭåĽ½
    0.06
    Activations Density 0.001%

    No Known Activations