© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 16277
    Prev
    Next
    INDEX
    Explanations

    say "shine"

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

    No Comments

    Negative Logits
     slog
    -18.63
    棍
    -18.25
    $log
    -18.13
    rok
    -18.00
     Tillerson
    -17.88
    ILog
    -17.63
    кси
    -17.50
    logging
    -17.38
    蝮
    -17.38
    lek
    -17.25
    POSITIVE LOGITS
    光辉
    23.38
    光泽
    21.50
     beauty
    21.50
     pearl
    20.50
    珍珠
    20.50
    珠
    20.38
    美景
    20.38
    美丽
    20.38
    明珠
    20.38
     shine
    20.25
    Activations Density 0.284%

    No Known Activations