© 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. 2097
    Prev
    Next
    INDEX
    Explanations

    say 拟

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

    No Comments

    Negative Logits
    erm
    -22.50
    ermal
    -19.75
    保守
    -19.75
    .Term
    -19.75
     terminals
    -19.50
    革命
    -19.38
     erm
    -18.50
    终端
    -18.38
    terminal
    -17.63
    段
    -17.50
    POSITIVE LOGITS
    拟
    50.75
    擬
    42.25
    模拟
    37.25
     proposal
    34.25
     sim
    32.25
     propose
    32.25
     proposals
    31.13
    sim
    31.00
    proposal
    30.75
     simulate
    29.88
    Activations Density 0.036%

    No Known Activations