© 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. 14147
    Prev
    Next
    INDEX
    Explanations

    say run

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

    No Comments

    Negative Logits
    信号
    -20.25
     signal
    -19.38
     signals
    -18.13
    signal
    -18.00
    .ajax
    -17.50
    signals
    -17.00
    Signal
    -16.63
     Signal
    -16.50
    (signal
    -16.13
    _signal
    -15.94
    POSITIVE LOGITS
    运行
    21.25
     run
    19.50
     Run
    19.25
     running
    19.13
     runs
    18.88
     frameworks
    18.88
     Running
    18.75
    Run
    18.63
     RUN
    17.75
    长效机制
    17.63
    Activations Density 0.472%

    No Known Activations