© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 16186
    Prev
    Next
    INDEX
    Explanations

    say "suffixes"

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

    No Comments

    Negative Logits
    尕
    -26.50
     Dawson
    -23.38
     Carlson
    -22.88
     Bowen
    -22.50
     Elaine
    -22.00
     Caldwell
    -21.63
     Robertson
    -21.50
    昶
    -21.38
    尉
    -21.25
     Lowe
    -20.63
    POSITIVE LOGITS
    蓉
    22.38
    蹴
    21.75
     Shak
    21.75
     Fus
    20.75
     Venus
    20.38
     Vik
    20.13
     Jug
    19.63
    /kubernetes
    19.50
     Toledo
    19.25
     Hend
    19.13
    Activations Density 4.212%

    No Known Activations