© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 34797
    Prev
    Next
    INDEX
    Explanations

    So I, it, you, with

    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
     Afinal
    -0.07
    æĸĩç«łäºĨ
    -0.07
    主åĬ¨åIJij
    -0.06
    ä»Ĭ天å°ıç¼ĸ
    -0.06
    åºĶæľīçļĦ
    -0.06
    缸åħ³æݨèįIJ
    -0.06
     kaç
    -0.06
    çľ
    -0.06
    hound
    -0.06
    ture
    -0.06
    POSITIVE LOGITS
    дем
    0.08
    åĽłæŃ¤åľ¨
    0.07
    laf
    0.07
    è¿Ļç§įåģļæ³ķ
    0.07
    æľīæѤ
    0.07
    erton
    0.07
    ocz
    0.07
    è¿Ļå°±æĺ¯æĪij
    0.07
    egis
    0.07
    à¹īà¸Ńม
    0.07
    Activations Density 0.221%

    No Known Activations