© 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. 2348
    Prev
    Next
    INDEX
    Explanations

    say "memorial"

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

    No Comments

    Negative Logits
     vec
    -22.75
    (Vec
    -22.50
     Vec
    -21.00
    .vec
    -20.88
     ctx
    -19.88
    (func
    -19.50
    (ctx
    -19.50
    ctx
    -19.38
    Ctx
    -19.25
     ret
    -18.75
    POSITIVE LOGITS
     Memorial
    32.00
     memorial
    29.13
    modal
    25.00
    Modal
    24.00
     memor
    23.50
    /modal
    22.75
    纪念
    22.25
     modal
    22.00
    terminal
    21.75
    .modal
    20.88
    Activations Density 0.125%

    No Known Activations