© 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. 54916
    Prev
    Next
    INDEX
    Explanations

    constant/uniform assumptions

    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
     Aprile
    -0.09
    ä¹ĭéķ¿
    -0.07
    еле
    -0.07
    ãĤıãģĸ
    -0.07
     Pull
    -0.07
    èĮ¶é¦Ļ
    -0.07
    евна
    -0.07
    nitz
    -0.06
    edom
    -0.06
    Pull
    -0.06
    POSITIVE LOGITS
     assumed
    0.09
     uniformly
    0.09
     uniform
    0.09
    æģĴå®ļ
    0.08
    åĿĩåĮĢ
    0.08
    缸åIJĮçļĦ
    0.08
     constant
    0.07
    ä¸Ģå¾ĭ
    0.07
    assume
    0.07
    åĿĩåĮĢçļĦ
    0.07
    Activations Density 0.045%

    No Known Activations