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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 320
    Prev
    Next
    INDEX
    Explanations

    say "Shakespeare"

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

    No Comments

    Negative Logits
     Kota
    -20.13
    稀土
    -18.88
     Skate
    -18.50
     granite
    -18.50
    ipop
    -18.38
     Korean
    -17.50
    °C
    -17.50
    新加坡
    -17.38
     CPF
    -17.25
    OOT
    -17.25
    POSITIVE LOGITS
     Shakespeare
    24.13
     Romeo
    19.63
     Elizabeth
    19.00
     Juliet
    18.13
     Alban
    17.38
    王子
    17.13
    actor
    16.63
    戏剧
    16.50
    莎
    16.50
     play
    16.50
    Activations Density 0.150%

    No Known Activations