© 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. 26154
    Prev
    Next
    INDEX
    Explanations

    specific properties of things

    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
     ìķĦëĭĪê³ł
    -0.11
    à¹ģละà¹Ģà¸Ľà¹ĩà¸Ļ
    -0.11
     ìĹĨê³ł
    -0.11
     ê²ĥìĿ´ê³ł
    -0.11
    à¹ģละมี
    -0.10
    ãģĵãģ¨ãĤĦ
    -0.10
    æĪĸèĢħ说
    -0.10
    åĴĮæľ¬
    -0.10
    à¹ģละà¹Ħมà¹Ī
    -0.10
    éĶĻ误æĪĸ
    -0.10
    POSITIVE LOGITS
     alike
    0.17
     serta
    0.14
     sowie
    0.13
    ãģ¨ãģĦãģ£ãģŁ
    0.13
     respectively
    0.10
    缸ç»ĵåIJĪçļĦ
    0.10
    缸ç»ĵåIJĪçļĦæĸ¹å¼ı
    0.09
     à¸ķลà¸Ńà¸Ķà¸Īà¸Ļ
    0.09
    çļĦåıĮéĩį
    0.09
    è¿Ļ两个
    0.09
    Activations Density 0.733%

    No Known Activations