© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14185
    Prev
    Next
    INDEX
    Explanations

    say "press"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    被盗
    -18.88
    电价
    -16.88
    システム
    -16.63
    双创
    -16.50
     équip
    -16.50
    霁
    -16.50
    ieee
    -16.38
    管理系统
    -16.00
    游击队
    -15.81
    酐
    -15.75
    POSITIVE LOGITS
     press
    31.38
    press
    31.13
    压
    30.13
     push
    29.50
    Press
    29.25
    push
    29.13
     Press
    28.88
     pressure
    28.75
     pressing
    28.25
     Pressure
    28.13
    Activations Density 0.355%

    No Known Activations