© 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. 2833
    Prev
    Next
    INDEX
    Explanations

    say "质"

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

    No Comments

    Negative Logits
    registry
    -23.50
    REG
    -19.63
     REG
    -19.50
     Registry
    -18.88
    reg
    -18.63
     reg
    -18.63
    百年
    -18.63
    _registry
    -18.50
     Reg
    -18.25
    -reg
    -17.75
    POSITIVE LOGITS
    质
    74.50
     Qual
    64.00
     qual
    64.00
    Qual
    61.75
    qual
    59.75
    質
    53.00
     qualitative
    52.50
    _qual
    52.50
     qualification
    50.50
    .qual
    49.00
    Activations Density 0.094%

    No Known Activations