© 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. 909
    Prev
    Next
    INDEX
    Explanations

    say city names

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

    No Comments

    Negative Logits
     Florida
    -22.75
    海南省
    -22.50
    Florida
    -21.88
    汾
    -21.88
     Thai
    -21.50
    海南
    -20.88
    加州
    -20.63
     Thái
    -20.38
    椰
    -20.25
    畹
    -19.63
    POSITIVE LOGITS
    连云港
    34.75
    宁波
    31.38
    宁波市
    30.63
    鄞
    30.50
     Belfast
    29.63
    赣
    29.50
    临沂
    29.25
    甬
    28.63
    赣州
    27.63
     Winnipeg
    27.13
    Activations Density 0.328%

    No Known Activations