© 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. 16268
    Prev
    Next
    INDEX
    Explanations

    say "dual"

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

    No Comments

    Negative Logits
     arcade
    -16.50
    -track
    -15.38
    örü
    -15.19
    背景
    -15.06
    圉
    -14.94
    론
    -14.75
    盘
    -14.69
    etwork
    -14.69
    -disc
    -14.56
    (DIS
    -14.56
    POSITIVE LOGITS
     dul
    20.75
    袅
    20.50
     twin
    19.88
    anol
    19.63
     dual
    19.38
    双
    19.13
    carbon
    19.00
     Dual
    18.63
    辣
    18.63
     dou
    18.00
    Activations Density 0.740%

    No Known Activations