© 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. 34889
    Prev
    Next
    INDEX
    Explanations

    X-ray related terms

    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
    ataire
    -0.10
    chaft
    -0.09
    æĺ¥æĿ¥
    -0.08
     konsek
    -0.08
    âĵĴ
    -0.08
    aporte
    -0.08
    chan
    -0.08
    ä¸įåīį
    -0.08
    RTL
    -0.07
    svar
    -0.07
    POSITIVE LOGITS
    ephy
    0.08
    /X
    0.07
    éħ¸éĴ¾
    0.07
    å·¥ä½ľèĢħ
    0.07
    ation
    0.07
     generated
    0.06
    ì§ķ
    0.06
     mining
    0.06
    rike
    0.06
    ศ
    0.06
    Activations Density 0.020%

    No Known Activations