© 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. 3108
    Prev
    Next
    INDEX
    Explanations

    board

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    元素
    -21.50
     element
    -18.75
    element
    -18.25
    	element
    -17.25
    -method
    -16.25
    妞
    -16.13
    Element
    -15.94
     elemento
    -15.81
    _element
    -15.75
    (element
    -15.50
    POSITIVE LOGITS
     board
    87.50
    板
    77.50
     Board
    75.00
    board
    74.50
    Board
    73.00
    	board
    71.50
    _board
    70.50
    .board
    69.50
    (board
    68.50
    -board
    68.50
    Activations Density 0.089%

    No Known Activations