© 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. 1663
    Prev
    Next
    INDEX
    Explanations

    [soil] => [soil]

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

    No Comments

    Negative Logits
    土壤
    -54.50
     soil
    -51.25
     Soil
    -47.00
     soils
    -45.00
    土
    -39.50
    泥土
    -36.00
    ⼟
    -27.50
     поч
    -26.13
    .SO
    -24.38
    土地
    -24.25
    POSITIVE LOGITS
    horse
    16.38
     num
    15.00
     Catalan
    14.50
    ęb
    14.50
    驹
    14.50
     horse
    14.44
     Jennifer
    14.19
     Num
    14.06
    psi
    14.00
     Jedi
    13.94
    Activations Density 0.158%

    No Known Activations