© 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. 13929
    Prev
    Next
    INDEX
    Explanations

    dictionary keys, pupils, cells

    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
    pa
    -0.07
    为ä¸Ń
    -0.07
    ç§ķ
    -0.07
    å½¢å¼ı
    -0.06
    æĺ¯ä¸Ń
    -0.06
    åģľä¸ļ
    -0.06
    ä¸įä¼ļåĽłä¸º
    -0.06
     appunto
    -0.06
     surprises
    -0.06
    ÙĨت
    -0.06
    POSITIVE LOGITS
    éħĮæĥħ
    0.08
    åij¨åħ¨
    0.08
    otted
    0.08
    ึà¸ĩ
    0.08
    使ä¹ĭ
    0.08
    åĽ¢
    0.08
    enburg
    0.08
    æ°ij建
    0.07
    ä¸Ģç»ıåıijçİ°
    0.07
    ä¸ĩèĥ½
    0.07
    Activations Density 0.275%

    No Known Activations