© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 925
    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
     Somali
    -28.88
    非洲
    -27.38
     Oman
    -26.00
     Somalia
    -24.75
     Tanzania
    -24.63
     Myanmar
    -24.00
    马来西亚
    -23.50
    梅州
    -23.13
    Mongo
    -23.13
     Mongo
    -22.88
    POSITIVE LOGITS
    工人
    21.13
     TS
    20.75
     bread
    20.00
     BS
    19.25
     RS
    18.88
     baker
    18.75
     CS
    18.38
    TS
    18.00
     workers
    17.88
    /ts
    17.88
    Activations Density 0.125%

    No Known Activations