© 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. 15445
    Prev
    Next
    INDEX
    Explanations

    say knight

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

    No Comments

    Negative Logits
    管理工作
    -19.00
    .atom
    -17.25
    Atoms
    -16.63
    水源
    -16.63
    交通大学
    -16.13
    OfWork
    -15.63
    公积金
    -15.63
    油田
    -15.56
    ynchronized
    -15.50
    油价
    -15.31
    POSITIVE LOGITS
    英雄
    26.25
     heroic
    26.25
     knight
    26.00
    侠
    25.88
    骑士
    25.38
    Hero
    25.00
     knights
    24.25
     warrior
    24.25
     Hero
    24.00
    .hero
    23.88
    Activations Density 0.234%

    No Known Activations