© 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. 1753
    Prev
    Next
    INDEX
    Explanations

    copper alloys

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

    No Comments

    Negative Logits
    铜
    -38.00
     copper
    -35.50
     Copper
    -31.00
    金属
    -28.75
     metal
    -27.88
     metals
    -27.75
     Cu
    -27.00
    metal
    -26.13
    Cu
    -25.63
    青铜
    -25.63
    POSITIVE LOGITS
    日本人
    18.88
     Islamic
    16.38
    ocal
    16.00
    engine
    15.94
    伊斯兰
    15.69
    流泪
    15.31
    词条
    15.00
    γ
    14.94
     Muslims
    14.81
     Japanese
    14.63
    Activations Density 0.055%

    No Known Activations