© 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. 396
    Prev
    Next
    INDEX
    Explanations

    northwest => Ancient Rus

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

    No Comments

    Negative Logits
    法国
    -27.38
     Bordeaux
    -26.50
    France
    -26.38
     France
    -25.75
    阿根廷
    -25.63
    フランス
    -25.63
     Marseille
    -25.50
     Franco
    -24.75
    French
    -23.63
     Spain
    -23.38
    POSITIVE LOGITS
    cs
    23.75
     Minnesota
    21.75
    tc
    21.25
     ds
    20.75
     cs
    19.75
    _cs
    19.00
    黑龙江
    18.75
     tc
    18.63
    /dc
    18.50
    ic
    18.38
    Activations Density 0.060%

    No Known Activations