© 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. 46825
    Prev
    Next
    INDEX
    Explanations

    start of latex environments

    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
    otle
    -0.08
     thereof
    -0.08
    anyl
    -0.08
    warzys
    -0.08
    æĪIJ为
    -0.07
     Conheça
    -0.07
    çļĦè¿ĩç¨ĭä¸Ń
    -0.07
    езде
    -0.07
    alet
    -0.07
    ÑħодÑĥ
    -0.07
    POSITIVE LOGITS
    æĸ°æĹ¶æľŁ
    0.07
    emann
    0.07
    ä½Ĩä¸įéĻIJäºİ
    0.06
    nev
    0.06
    说æĿ¥
    0.06
    ãģĦãģijãģªãģĦ
    0.06
    ãģĬ
    0.06
    ä¸Ģè¦ģ
    0.06
    begin
    0.06
    ä¸Ģæĸ¹éĿ¢æĺ¯
    0.06
    Activations Density 0.001%

    No Known Activations