© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14535
    Prev
    Next
    INDEX
    Explanations

    say ice

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

    No Comments

    Negative Logits
    进城
    -18.75
    顾客
    -18.50
    objs
    -17.75
    产品
    -17.63
    类产品
    -17.50
    /products
    -17.00
     fert
    -16.75
    .Products
    -16.50
    .stat
    -15.94
    客户的
    -15.94
    POSITIVE LOGITS
    冰
    18.75
    冰雪
    18.25
     ice
    18.25
     Antarctica
    18.13
    Ice
    17.63
     Ice
    16.75
     snow
    16.63
    雪花
    16.38
    ice
    16.38
     frozen
    15.88
    Activations Density 0.088%

    No Known Activations