© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15582
    Prev
    Next
    INDEX
    Explanations

    say square

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

    No Comments

    Negative Logits
    .digest
    -18.50
    ⇀
    -17.75
     brush
    -17.13
    的手
    -16.88
    Gesture
    -16.75
    督
    -16.13
    digest
    -15.88
    gist
    -15.69
    asin
    -15.63
    纠
    -15.50
    POSITIVE LOGITS
    乌
    20.63
     squares
    20.50
     UCS
    19.63
     square
    19.00
    古城
    18.13
     Square
    18.00
     Queens
    18.00
     квар
    17.75
     Honduras
    17.75
    square
    17.50
    Activations Density 1.496%

    No Known Activations