© 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. 977
    Prev
    Next
    INDEX
    Explanations

    say Jefferson

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

    No Comments

    Negative Logits
    菏泽
    -28.13
    梅州
    -22.75
     Winnipeg
    -22.75
     Manitoba
    -21.63
     Calgary
    -21.50
    郓
    -21.50
    赣
    -21.38
    东莞
    -20.63
    赣州
    -20.63
     Sask
    -20.38
    POSITIVE LOGITS
     Jefferson
    41.75
    Jeff
    30.75
     Lafayette
    26.75
    詹姆斯
    25.88
     jean
    24.88
    Jean
    24.75
    华盛顿
    24.50
     Philippe
    24.25
     Jean
    24.13
    Thomas
    21.88
    Activations Density 0.077%

    No Known Activations