© 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. 63462
    Prev
    Next
    INDEX
    Explanations

    high precision

    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
    ickest
    -0.10
    èIJ½èIJ½
    -0.09
    æĽ´æĸ¹ä¾¿
    -0.08
    stag
    -0.08
     hearty
    -0.08
     easiest
    -0.08
     Helper
    -0.08
    ICAST
    -0.08
    æĸ¹ä¾¿çļĦ
    -0.07
    å¤ļåģļ
    -0.07
    POSITIVE LOGITS
     precision
    0.18
    ç²¾å¯Ĩ
    0.17
    precision
    0.17
    精度
    0.16
     precise
    0.16
     Precision
    0.15
    Precision
    0.15
    精确
    0.14
    ç²¾ç»Ĩ
    0.14
    é«ĺ精度
    0.13
    Activations Density 0.188%

    No Known Activations