© 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. 2430
    Prev
    Next
    INDEX
    Explanations

    say "simulation"

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

    No Comments

    Negative Logits
     erm
    -16.25
    Terr
    -15.88
     smo
    -15.00
    yı
    -14.81
    wig
    -14.81
    scp
    -14.69
    erras
    -14.63
     Terr
    -14.63
    uther
    -14.31
     extrem
    -14.19
    POSITIVE LOGITS
     simulation
    92.50
     sim
    92.50
    Sim
    89.00
    模拟
    88.50
    (sim
    88.50
     Sim
    86.00
     simulate
    85.50
    sim
    84.50
     Simulation
    84.50
     simulated
    82.50
    Activations Density 0.384%

    No Known Activations