© 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. 1515
    Prev
    Next
    INDEX
    Explanations

    say "image" words

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

    No Comments

    Negative Logits
    波兰
    -32.75
     Poland
    -31.38
     Polish
    -30.88
    安徽省
    -29.75
    安徽
    -27.50
    Pol
    -27.13
     polish
    -25.25
    _POL
    -25.13
     pol
    -24.50
     Pol
    -24.00
    POSITIVE LOGITS
    jpeg
    18.63
     Salmon
    18.50
    Images
    18.38
    魚
    18.38
     Images
    17.88
     images
    17.38
    鱼
    17.38
    images
    16.75
    Image
    16.75
    sal
    16.50
    Activations Density 0.101%

    No Known Activations