© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-1.7B
    3. 26-LLAMASCOPE-2-LORSA-16K-K64
    4. 434
    Prev
    Next
    INDEX
    Explanations

    province names

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

    No Comments

    Negative Logits
     Ri
    -20.88
     Stamford
    -20.38
    北京市
    -20.25
    (tf
    -20.00
     Nak
    -19.88
     PMC
    -19.88
     Aviv
    -19.38
     tf
    -18.63
     Ish
    -18.50
     Naj
    -18.38
    POSITIVE LOGITS
    我省
    50.75
    全省
    46.75
    省内
    45.75
    省政府
    45.00
    省
    43.75
    省委
    43.00
    省份
    36.75
     Oregon
    35.25
    青海省
    33.75
    省教育
    32.75
    Activations Density 0.158%

    No Known Activations