© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 235
    Prev
    Next
    INDEX
    Explanations

    say historical figures

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

    No Comments

    Negative Logits
    阿根廷
    -24.13
     Argentine
    -24.13
    Argentina
    -23.25
    红茶
    -22.63
    =tf
    -22.25
    挪威
    -21.63
    .tf
    -21.50
     Trinidad
    -21.25
     Norway
    -21.13
     Antarctica
    -21.00
    POSITIVE LOGITS
    刘邦
    42.50
    楚
    40.75
    秦
    31.13
    秦国
    29.50
     Qin
    29.00
     κ
    26.88
     Caesar
    24.75
     Kurdish
    24.00
    韩
    24.00
     Indiana
    23.00
    Activations Density 0.063%

    No Known Activations