© 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. 1837
    Prev
    Next
    INDEX
    Explanations

    say "fish"

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

    No Comments

    Negative Logits
    伊朗
    -31.13
     Iran
    -29.63
    陕西
    -28.75
    陕西省
    -26.63
    Iran
    -26.25
    西安
    -26.00
     Iranian
    -25.75
    西安市
    -24.50
     Persian
    -22.75
     Iranians
    -21.38
    POSITIVE LOGITS
    鱼类
    22.50
    鱼
    19.13
    设备
    18.88
     fish
    18.13
    Fish
    17.88
    渔民
    17.88
    fish
    17.75
     Fish
    17.38
    /vector
    17.38
     device
    17.25
    Activations Density 0.149%

    No Known Activations