© 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. 2760
    Prev
    Next
    INDEX
    Explanations

    say "继"

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

    No Comments

    Negative Logits
     Dem
    -24.25
     DEM
    -23.38
    Dem
    -22.38
    Pen
    -22.25
     dem
    -21.13
     demos
    -20.88
     Pen
    -20.63
    _dem
    -20.38
    -dem
    -20.25
    徐
    -20.13
    POSITIVE LOGITS
     rel
    48.75
    继
    46.50
    (rel
    45.00
    Rel
    42.00
     Rel
    40.75
    rel
    40.00
    -rel
    37.25
     relay
    36.75
    繼
    36.50
     REL
    36.00
    Activations Density 0.057%

    No Known Activations