© 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. 1945
    Prev
    Next
    INDEX
    Explanations

    food => fish

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

    No Comments

    Negative Logits
     fish
    -58.25
    鱼
    -57.25
    Fish
    -55.50
     Fish
    -53.50
    魚
    -53.00
    鱼类
    -52.25
    fish
    -51.50
     fishes
    -48.00
     Fisher
    -40.75
     fishing
    -40.25
    POSITIVE LOGITS
    inox
    16.13
     WC
    15.38
     Dallas
    15.19
     Islamic
    15.06
    伊斯兰
    15.00
    陕西省
    13.69
    咸阳
    13.63
    _blog
    13.56
    .twitter
    13.56
    _mapper
    13.38
    Activations Density 0.144%

    No Known Activations