© 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. 2698
    Prev
    Next
    INDEX
    Explanations

    say "Marg" words

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

    No Comments

    Negative Logits
     Ser
    -21.75
    .ser
    -21.50
    -ser
    -20.00
    Ser
    -20.00
     ser
    -20.00
    et
    -18.00
     deser
    -17.75
    ser
    -17.50
     deserialize
    -17.25
    _ser
    -17.25
    POSITIVE LOGITS
     Marg
    76.50
    Marg
    73.50
     marg
    72.00
     marginal
    67.00
     margin
    62.50
     margins
    60.00
     Margin
    56.50
    margin
    54.50
    Margin
    53.00
    边际
    52.25
    Activations Density 0.055%

    No Known Activations