© 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. 2945
    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
     thermostat
    -20.88
     Skate
    -19.63
    rsa
    -19.25
    weather
    -19.25
    矿泉水
    -18.88
     astrology
    -18.50
    星座
    -17.63
    雪花
    -17.38
     skating
    -17.38
     asteroid
    -17.38
    POSITIVE LOGITS
    工人
    19.50
     Workers
    17.63
     workers
    17.00
    Workers
    16.50
    革命
    16.25
    建设
    15.88
    workers
    15.69
     worker
    15.19
    社会主义
    15.13
    资产
    15.00
    Activations Density 0.166%

    No Known Activations