© 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. 44569
    Prev
    Next
    INDEX
    Explanations

    merge sorted arrays

    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
    Negative Logits
    iado
    -0.08
     targets
    -0.08
    _android
    -0.07
     hab
    -0.07
    targets
    -0.07
    rava
    -0.07
    ä¸İä¼Ĺä¸įåIJĮ
    -0.07
    Targets
    -0.07
    stp
    -0.07
    èĢĺ
    -0.07
    POSITIVE LOGITS
    åıĮæĸ¹
    0.10
    åıĮæĸ¹çļĦ
    0.09
     displaced
    0.09
     displ
    0.08
    åıĮæĸ¹åľ¨
    0.08
    æĿ¥èĩª
    0.08
    ä¼łçľŁ
    0.08
    æıĴ
    0.07
    _merge
    0.07
    putc
    0.07
    Activations Density 0.004%

    No Known Activations