© 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. 1860
    Prev
    Next
    INDEX
    Explanations

    soil

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

    No Comments

    Negative Logits
     earth
    -55.75
     Earth
    -53.25
    Earth
    -51.50
    earth
    -47.75
    地球
    -46.25
    -earth
    -42.75
    ARTH
    -31.38
    大地
    -28.75
    地球上
    -26.88
    arth
    -23.38
    POSITIVE LOGITS
    ymm
    15.81
     Alonso
    15.81
    ム
    14.88
    宫殿
    14.88
    算法
    14.81
    心理学
    14.75
     Algorithms
    14.63
    sym
    14.56
    心理
    14.44
    Sym
    14.38
    Activations Density 0.132%

    No Known Activations