© 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. 2500
    Prev
    Next
    INDEX
    Explanations

    say "Simon"

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

    No Comments

    Negative Logits
    (det
    -18.75
    Det
    -18.38
    kı
    -17.00
    -det
    -16.38
    det
    -16.13
    .det
    -16.13
     Det
    -15.75
    (Int
    -15.56
     fmt
    -15.13
    .recycle
    -14.88
    POSITIVE LOGITS
     Simon
    68.00
    Simon
    64.50
     sim
    50.25
     simulation
    49.00
    (sim
    47.75
     SIM
    47.00
     Simulation
    46.75
    sim
    46.00
     simulated
    45.00
    Simulation
    44.75
    Activations Density 0.038%

    No Known Activations