© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 3059
    Prev
    Next
    INDEX
    Explanations

    say empire

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

    No Comments

    Negative Logits
     pot
    -16.88
     annotation
    -16.63
     GEN
    -16.25
     Utils
    -16.13
     annotations
    -15.94
     generics
    -15.94
     Ser
    -15.88
     gen
    -15.88
    (Utils
    -15.81
     detector
    -15.69
    POSITIVE LOGITS
    帝国
    49.25
     empire
    48.50
    Emp
    46.75
     Empire
    46.50
     Emp
    45.25
     imperial
    43.75
    emp
    43.50
     em
    43.00
     empirical
    38.75
     emperor
    38.50
    Activations Density 0.154%

    No Known Activations