© 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. 543
    Prev
    Next
    INDEX
    Explanations

    say US presidents

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

    No Comments

    Negative Logits
    郯
    -21.13
    米兰
    -21.00
     Rune
    -20.13
    济南
    -19.00
     Johan
    -19.00
    赣
    -18.75
    轨道交通
    -18.75
    景德镇
    -18.63
    骑行
    -18.63
     Railway
    -18.63
    POSITIVE LOGITS
    白宫
    32.25
     Nixon
    29.25
     Eisenhower
    28.25
     Vietnam
    27.00
     JFK
    27.00
     Reagan
    24.75
    尼克
    24.50
     Truman
    24.50
    在美国
    24.38
     Kennedy
    23.38
    Activations Density 0.302%

    No Known Activations