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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14095
    Prev
    Next
    INDEX
    Explanations

    say poetry

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

    No Comments

    Negative Logits
    DCF
    -19.63
    理事长
    -17.63
    SystemService
    -17.25
    牌照
    -17.25
    窗口
    -16.63
    isdiction
    -16.38
     duty
    -16.13
    DOCUMENT
    -16.00
    信号
    -15.94
    Startup
    -15.81
    POSITIVE LOGITS
     poem
    44.00
    诗
    43.25
     poetry
    43.25
    詩
    43.00
    诗歌
    43.00
     poems
    42.75
     poets
    41.50
    -po
    40.75
     poet
    40.25
    (po
    40.25
    Activations Density 0.895%

    No Known Activations