© 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. 2283
    Prev
    Next
    INDEX
    Explanations

    say emperor

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

    No Comments

    Negative Logits
    (ref
    -16.88
     Evans
    -16.88
     REF
    -16.75
    反射
    -16.63
    .ref
    -16.63
     Reflex
    -16.63
    -ref
    -16.50
    (annotation
    -16.38
     Relations
    -16.25
    reflection
    -16.13
    POSITIVE LOGITS
    帝
    50.75
     dem
    36.50
     Dem
    33.00
    Dem
    31.38
    -dem
    30.75
    dem
    30.38
     emperor
    28.63
    帝国
    27.88
     imperial
    27.63
    _dem
    25.88
    Activations Density 0.051%

    No Known Activations