© 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. 933
    Prev
    Next
    INDEX
    Explanations

    say foreign place names

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

    No Comments

    Negative Logits
    黄山
    -24.25
    汶
    -23.88
    Oregon
    -23.75
    _AX
    -23.75
     Tacoma
    -23.63
     UW
    -23.25
     Oregon
    -23.13
    兖
    -23.13
     Wyoming
    -23.00
    (rx
    -22.75
    POSITIVE LOGITS
     Украины
    22.38
    沈阳
    21.88
     Mohamed
    21.75
    温州
    21.25
    是韩国
    20.88
     Tamil
    20.63
    吉林省
    20.50
    郑州市
    20.00
    在广州
    19.88
    �
    19.63
    Activations Density 0.886%

    No Known Activations