© 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. 64524
    Prev
    Next
    INDEX
    Explanations

    research or study initiation

    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
    使åħ¶
    -0.09
     thereof
    -0.09
    使å®ĥ
    -0.09
    æľīæѤ
    -0.08
    åįİé¾Ļ
    -0.08
    çļĦåħ¶ä»ĸ
    -0.08
     membuatnya
    -0.08
    使ä¹ĭ
    -0.08
    äºĨè¿Ļ个
    -0.07
    å°ĩåħ¶
    -0.07
    POSITIVE LOGITS
    对ä¸Ģ个
    0.11
     двÑĥм
    0.09
    对äºİä¸Ģ个
    0.08
    对ä¸ĢäºĽ
    0.08
    åľ¨ä¸Ģ
    0.08
    为ä¸Ģ
    0.08
    æŁIJ
    0.08
     suatu
    0.07
    两个æĸ¹éĿ¢
    0.07
    两类
    0.07
    Activations Density 1.160%

    No Known Activations