© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1534
    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
     European
    -55.00
    欧洲
    -54.75
    European
    -51.25
     Europe
    -50.00
    Eu
    -47.75
     Europeans
    -46.75
     european
    -45.50
    Europe
    -45.25
     Europa
    -45.00
     Eu
    -44.75
    POSITIVE LOGITS
    字
    18.88
    诗句
    17.00
    詩
    16.50
    诗
    16.25
     Jackson
    15.00
     poetry
    15.00
    enton
    14.94
     poems
    14.88
    诗词
    14.88
    矸
    14.81
    Activations Density 0.205%

    No Known Activations