© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1270
    Prev
    Next
    INDEX
    Explanations

    物质

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

    No Comments

    Negative Logits
    物质
    -37.75
     material
    -27.75
    Material
    -27.50
    物资
    -26.63
     Material
    -26.13
    .material
    -25.88
    _material
    -25.50
    material
    -25.25
    物
    -24.88
    -material
    -24.63
    POSITIVE LOGITS
    键盘
    15.44
     Catalan
    15.31
    editor
    14.63
    frican
    14.25
    熊猫
    14.19
     Edited
    14.13
    编辑
    14.06
    egal
    13.38
    .RestController
    13.31
     Wilmington
    13.31
    Activations Density 0.063%

    No Known Activations