© 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. 1036
    Prev
    Next
    INDEX
    Explanations

    say marine

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

    No Comments

    Negative Logits
    泪
    -32.50
     tears
    -31.38
    泪水
    -30.75
    眼泪
    -29.63
    淚
    -28.25
     tear
    -27.88
     Tears
    -27.00
    流泪
    -26.00
     tearing
    -22.13
     crying
    -20.88
    POSITIVE LOGITS
    海岛
    20.13
    港口
    20.13
     Motorola
    17.75
    珊瑚
    17.63
    Mar
    17.25
     marine
    17.25
    Unmarshaller
    16.88
    海滩
    16.63
    UUID
    15.69
    岛上
    15.63
    Activations Density 0.108%

    No Known Activations