© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 910
    Prev
    Next
    INDEX
    Explanations

    say "Han"

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

    No Comments

    Negative Logits
    Fd
    -19.00
    ValuePair
    -16.50
     LSU
    -16.25
    (ft
    -16.13
    .pg
    -16.00
    fv
    -16.00
    蘑菇
    -15.94
     Baton
    -15.88
    idor
    -15.75
    枞
    -15.69
    POSITIVE LOGITS
    汉
    63.50
    漢
    56.75
     Han
    51.25
    Han
    44.00
    ハン
    32.50
    刘邦
    31.38
    汉族
    30.25
    han
    28.63
     stem
    28.25
     han
    28.13
    Activations Density 0.179%

    No Known Activations