© 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. 1891
    Prev
    Next
    INDEX
    Explanations

    [soil] => [soil Loam]

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

    No Comments

    Negative Logits
     зрения
    -18.63
    洮
    -18.25
    obil
    -18.13
    ious
    -17.13
    燃烧
    -16.88
    燒
    -16.75
    圈
    -16.50
    堃
    -16.38
    št
    -16.25
    urat
    -16.13
    POSITIVE LOGITS
    太子
    16.75
    ง
    16.63
    (css
    14.63
    (MenuItem
    14.19
    ucas
    13.88
     kings
    13.81
    (light
    13.63
    Macro
    13.50
     LoginForm
    13.50
    csv
    13.44
    Activations Density 0.136%

    No Known Activations