© 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. 2680
    Prev
    Next
    INDEX
    Explanations

    century

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

    No Comments

    Negative Logits
    Seg
    -20.50
    Var
    -20.13
     Repo
    -19.25
    Mat
    -19.00
     Mem
    -18.75
    Resp
    -18.75
     dev
    -18.50
     Mat
    -18.38
    Segments
    -18.38
     Seg
    -18.25
    POSITIVE LOGITS
    世纪
    34.75
     century
    34.25
     Century
    32.75
    cent
    31.13
    Century
    31.13
    百
    29.75
     mill
    29.50
     hundred
    28.63
    -century
    28.63
     cent
    28.50
    Activations Density 0.133%

    No Known Activations