© 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. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 3248
    Prev
    Next
    INDEX
    Explanations

    say "window"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    won
    -16.38
    _MESH
    -16.00
    otti
    -15.75
     supern
    -15.50
    aran
    -15.44
    odial
    -15.31
    oko
    -15.25
     desserts
    -14.44
     sucker
    -14.31
    烬
    -14.25
    POSITIVE LOGITS
     window
    71.50
    窗口
    70.00
    window
    66.00
     Window
    66.00
    Window
    61.50
    	window
    61.00
    _window
    59.50
    -window
    59.00
    (window
    58.50
    .window
    58.00
    Activations Density 0.105%

    No Known Activations