© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15150
    Prev
    Next
    INDEX
    Explanations

    say "sand"

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

    No Comments

    Negative Logits
    /goto
    -16.38
    _vue
    -16.25
    plist
    -16.13
    健康管理
    -15.94
    opensource
    -15.56
    (logging
    -15.50
    typing
    -15.38
    省公安厅
    -15.31
    (pol
    -15.00
    州市
    -14.94
    POSITIVE LOGITS
    沙
    24.63
     sand
    23.88
     sands
    23.75
    沙漠
    23.00
     Desert
    22.25
     desert
    22.13
    砂
    20.63
     salt
    19.75
     Sand
    19.63
     Sands
    19.50
    Activations Density 0.162%

    No Known Activations