© 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. 1387
    Prev
    Next
    INDEX
    Explanations

    say province names

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

    No Comments

    Negative Logits
    河南
    -35.25
    河南省
    -33.75
    Ohio
    -32.75
     Ohio
    -31.63
    郑州
    -24.50
     ohio
    -23.75
    中原
    -23.13
    洧
    -20.50
    Penn
    -20.50
     Pennsylvania
    -20.50
    POSITIVE LOGITS
    菌
    16.25
    -ps
    16.00
     breast
    16.00
    抗菌
    15.56
    海上
    15.44
     Norway
    15.44
    岚
    15.38
    浒
    15.31
     psychologist
    15.31
     Tax
    15.06
    Activations Density 0.113%

    No Known Activations