© 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. 1554
    Prev
    Next
    INDEX
    Explanations

    say "fight"

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

    No Comments

    Negative Logits
     fly
    -38.25
     flying
    -36.25
     flight
    -36.25
     Fly
    -34.75
    Fly
    -34.50
    Flight
    -33.50
    飞行
    -33.00
     flies
    -32.75
     flown
    -32.75
    飞
    -32.50
    POSITIVE LOGITS
     tensor
    16.75
    tensor
    16.38
    媒介
    16.25
     Muse
    15.88
     med
    15.88
     Hamilton
    15.50
    机器
    15.19
    社交媒体
    15.06
    _xml
    14.94
    /xml
    14.81
    Activations Density 0.084%

    No Known Activations