© 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. 1680
    Prev
    Next
    INDEX
    Explanations

    do not say sea

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

    No Comments

    Negative Logits
     sea
    -42.75
     Sea
    -42.50
    Sea
    -41.00
    海
    -36.50
    sea
    -36.00
     seas
    -34.50
    海水
    -33.00
     SEA
    -33.00
    SEA
    -28.75
    海上
    -28.75
    POSITIVE LOGITS
     Banc
    19.13
     code
    16.63
    engine
    15.75
    -token
    15.50
    	widget
    15.31
    彝
    15.31
    .widget
    15.25
    Motor
    15.06
    电机
    15.06
     motor
    14.88
    Activations Density 0.089%

    No Known Activations