© 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. 14122
    Prev
    Next
    INDEX
    Explanations

    say substitute

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

    No Comments

    Negative Logits
     movement
    -25.13
    运动
    -24.63
     movimiento
    -22.00
     Movement
    -21.88
    动作
    -21.63
     motion
    -21.63
    運動
    -20.88
    Movement
    -20.75
    movement
    -20.75
    驱动
    -20.13
    POSITIVE LOGITS
     substitute
    18.75
     substit
    17.88
    敞开
    17.63
     balance
    17.13
     substitutions
    16.38
     substituted
    16.13
     substitutes
    16.00
    balance
    15.88
     balances
    15.88
    替代
    15.75
    Activations Density 0.722%

    No Known Activations