© 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. 2524
    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
     Ser
    -19.13
    (serial
    -19.13
     Pol
    -18.13
    (pol
    -18.13
    .serial
    -16.50
     moderators
    -16.38
    _pol
    -16.13
     ser
    -16.13
    unger
    -16.00
     pol
    -15.88
    POSITIVE LOGITS
     margin
    69.50
     Margin
    64.50
    margin
    61.00
    Margin
    60.50
     margins
    58.00
    _margin
    53.25
     Marg
    51.25
    .margin
    50.75
    	margin
    50.75
     marg
    50.75
    Activations Density 0.040%

    No Known Activations