© 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. 1883
    Prev
    Next
    INDEX
    Explanations

    do not say snow

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

    No Comments

    Negative Logits
     snow
    -44.00
    雪
    -43.75
     Snow
    -40.25
    snow
    -40.00
    Snow
    -39.25
    雪花
    -38.25
     snowy
    -36.50
    白雪
    -34.75
    冰雪
    -33.75
    雪山
    -31.13
    POSITIVE LOGITS
     Portugal
    18.75
    .ps
    15.13
    马来西亚
    15.00
     Palestinian
    14.63
    工艺
    14.44
    卡
    14.00
    电路
    14.00
    葡萄牙
    13.88
     Malaysia
    13.88
     Kuala
    13.75
    Activations Density 0.061%

    No Known Activations