© 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. 1984
    Prev
    Next
    INDEX
    Explanations

    [ice] => [ice]

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

    No Comments

    Negative Logits
     ice
    -48.75
    冰
    -46.00
     Ice
    -43.75
    Ice
    -40.75
    ICE
    -36.50
    ice
    -34.50
     ICE
    -34.25
    冰雪
    -34.25
     icy
    -33.00
    iced
    -31.63
    POSITIVE LOGITS
    �
    16.63
    ului
    15.38
    .Html
    15.00
     Scripture
    14.88
    apers
    14.25
    unsafe
    13.75
     safety
    13.69
    .SQL
    13.56
     Stories
    13.56
     Script
    13.50
    Activations Density 0.101%

    No Known Activations