© 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. 3241
    Prev
    Next
    INDEX
    Explanations

    say "John"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    组件
    -18.38
     component
    -17.75
    (component
    -17.75
    	component
    -16.88
     equation
    -16.50
    (configuration
    -16.25
     Component
    -16.13
    component
    -15.88
    组
    -15.69
     entry
    -14.94
    POSITIVE LOGITS
     John
    31.50
    John
    28.00
     JOHN
    26.63
     sample
    26.00
    sample
    25.88
     john
    25.00
    Sample
    24.75
     personal
    24.38
    /sample
    24.25
    约翰
    24.13
    Activations Density 0.332%

    No Known Activations