© 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. 3101
    Prev
    Next
    INDEX
    Explanations

    say square

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     Component
    -17.38
    组件
    -16.75
    组
    -15.81
    sut
    -15.50
    Spr
    -15.00
     component
    -14.88
    	property
    -14.31
    	component
    -14.25
     cheeks
    -14.25
    Component
    -14.19
    POSITIVE LOGITS
    square
    40.50
     square
    40.25
    _square
    35.50
     Square
    34.75
    Square
    34.25
    .square
    31.13
    (square
    28.50
    -square
    27.88
    quare
    27.13
    方
    26.63
    Activations Density 0.043%

    No Known Activations