© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15688
    Prev
    Next
    INDEX
    Explanations

    animal-drawn wagons

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

    No Comments

    Negative Logits
     chlorine
    -18.25
    净水
    -17.75
    清理
    -17.63
    脆
    -17.25
     Quartz
    -17.25
    瘋
    -17.13
    晶体
    -17.00
     fluoride
    -16.88
    лим
    -16.75
    クリ
    -16.25
    POSITIVE LOGITS
    车
    25.00
     wagon
    24.63
    車
    22.88
     carts
    22.75
    驾车
    22.38
    驮
    21.88
     saddle
    21.88
     driver
    21.75
    驱动
    21.63
     drivers
    21.38
    Activations Density 0.224%

    No Known Activations