© 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. 1028
    Prev
    Next
    INDEX
    Explanations

    say land terms

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

    No Comments

    Negative Logits
    饮品
    -23.00
    奶茶
    -20.75
     refriger
    -20.63
     iceberg
    -20.50
    冷链
    -20.38
    drink
    -20.25
    心脏
    -19.75
    中央空调
    -19.63
    血液
    -19.63
     frosting
    -19.50
    POSITIVE LOGITS
    宅
    17.25
     WV
    16.88
    矿区
    16.50
    建设用地
    14.50
    坐
    14.25
     Site
    13.94
    耕地
    13.88
    总投资
    13.63
     Tomb
    13.50
    .getModel
    13.44
    Activations Density 0.074%

    No Known Activations