© 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. 1593
    Prev
    Next
    INDEX
    Explanations

    say "boat"

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

    No Comments

    Negative Logits
     exercise
    -41.00
     exercises
    -38.00
    exercise
    -36.50
     Exercise
    -36.00
    Exercise
    -34.75
     Exercises
    -33.25
     exercising
    -31.25
     exercised
    -29.88
     AX
    -29.50
    AX
    -29.38
    POSITIVE LOGITS
    军
    21.88
    海军
    20.13
    軍
    18.25
     boat
    17.50
    渔船
    17.00
    boat
    16.88
    地图
    16.63
    映
    16.63
    军人
    16.25
    船只
    16.13
    Activations Density 0.091%

    No Known Activations