© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14139
    Prev
    Next
    INDEX
    Explanations

    say "route"

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

    No Comments

    Negative Logits
     STATE
    -23.63
     position
    -22.38
     state
    -22.25
     positions
    -22.00
    状态
    -21.38
    position
    -21.38
     Position
    -21.25
     setPosition
    -21.13
    state
    -20.88
     states
    -20.38
    POSITIVE LOGITS
    送
    16.13
    送去
    16.00
     resolution
    15.38
     routes
    15.13
     марш
    15.00
    routes
    14.94
    リンク
    14.69
     link
    14.63
     Conduct
    14.63
     route
    14.50
    Activations Density 0.958%

    No Known Activations