© 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. 14577
    Prev
    Next
    INDEX
    Explanations

    say Irish

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

    No Comments

    Negative Logits
    亚马逊
    -21.13
    (sigma
    -18.25
    科学家
    -18.13
    科學
    -17.38
    实验室
    -17.38
    bucket
    -17.00
     capacitor
    -17.00
    埋
    -16.63
    .bucket
    -16.63
     Scientists
    -16.63
    POSITIVE LOGITS
    爱尔兰
    33.00
     Irish
    31.88
     Ireland
    31.63
     Gael
    28.38
    reland
    27.75
    Ir
    26.88
     Dublin
    25.50
     Belfast
    23.38
    湖北省
    23.38
    鄂
    22.63
    Activations Density 0.197%

    No Known Activations