© 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. 1628
    Prev
    Next
    INDEX
    Explanations

    mineral

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

    No Comments

    Negative Logits
     med
    -25.75
    矿物
    -25.50
    矿山
    -24.50
    矿物质
    -24.00
    矿
    -23.50
     mineral
    -23.38
    矿业
    -23.13
     Mining
    -22.63
     mining
    -22.25
     Mineral
    -22.00
    POSITIVE LOGITS
    eng
    17.25
     Buckley
    16.00
     Ball
    15.13
    football
    15.06
     Arab
    14.94
     Greeks
    14.88
     Texans
    14.44
     Yankee
    14.44
    Read
    14.38
     Construct
    14.38
    Activations Density 0.089%

    No Known Activations