© 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. 1886
    Prev
    Next
    INDEX
    Explanations

    arc‑related terms

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

    No Comments

    Negative Logits
    弧
    -22.63
    (arc
    -22.50
    .arc
    -21.88
     arc
    -21.50
     silk
    -20.63
     arcs
    -19.38
    材料
    -18.88
    Arc
    -18.88
     api
    -18.63
     Arc
    -18.25
    POSITIVE LOGITS
    鲁能
    18.50
     München
    17.13
     painting
    16.75
    心理健康
    16.13
     painted
    16.00
    ssh
    15.88
    浮动
    15.88
    MySQL
    15.81
     cube
    15.69
    公正
    15.69
    Activations Density 0.078%

    No Known Activations