© 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. 2661
    Prev
    Next
    INDEX
    Explanations

    say "workers"

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

    No Comments

    Negative Logits
    音乐
    -21.13
    乐器
    -19.00
    野生动物
    -19.00
    海水
    -18.75
    音樂
    -18.38
    羚
    -18.38
    odiac
    -17.88
    kea
    -17.88
     music
    -17.88
    动物
    -17.63
    POSITIVE LOGITS
    Workers
    29.25
     workers
    28.50
    工人
    28.25
     Workers
    28.13
     prolet
    26.25
     worker
    25.88
    (worker
    25.00
    workers
    24.88
     Trotsky
    24.00
    worker
    23.50
    Activations Density 0.368%

    No Known Activations