© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 2843
    Prev
    Next
    INDEX
    Explanations

    甲乙双方

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

    No Comments

    Negative Logits
    ↵		
↵
    -20.38
    ↵	
↵
    -20.25
    ...
↵
    -19.13
    \
↵
    -18.63
    &nbsp
    -18.50
     \
↵
    -17.38
    ...</
    -17.38
    ↵↵
    -16.75
    •↵↵
    -16.00
     •
    -15.63
    POSITIVE LOGITS
    乙方
    41.00
    ________
    40.25
     ______
    39.50
    _____
    38.25
    甲方
    37.50
    ____________
    36.50
     _____
    36.50
    ____
    35.25
    ________________
    34.75
     __________________
    34.75
    Activations Density 0.039%

    No Known Activations