© 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. 2702
    Prev
    Next
    INDEX
    Explanations

    say margin

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

    No Comments

    Negative Logits
    quant
    -20.50
     quantitative
    -20.13
     quant
    -18.75
    Quant
    -18.75
    Registration
    -17.88
     regist
    -17.75
     Registration
    -17.50
    _quant
    -17.50
     Quant
    -17.50
    注册
    -17.38
    POSITIVE LOGITS
    边
    55.50
    邊
    44.25
     Marg
    39.00
    Marg
    38.50
     marg
    36.50
     marginal
    35.50
    边上
    35.50
     margin
    34.75
    边际
    34.00
    margin
    32.75
    Activations Density 0.052%

    No Known Activations