© 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. 14200
    Prev
    Next
    INDEX
    Explanations

    say "exchange"

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

    No Comments

    Negative Logits
     loadImage
    -17.50
    收紧
    -16.50
    裂
    -16.25
    resolved
    -15.88
    (load
    -15.50
    	parser
    -15.38
     parser
    -15.13
    _load
    -15.06
    Tpl
    -14.63
    打包
    -14.44
    POSITIVE LOGITS
    交换
    52.50
    交流
    51.75
     exchange
    51.75
     exchanges
    49.00
    exchange
    45.75
     exchanging
    45.25
    交互
    45.25
     interchange
    45.00
     exchanged
    45.00
     Exchange
    45.00
    Activations Density 0.777%

    No Known Activations