© 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
    2. Qwen3-1.7B
    3. 26-LLAMASCOPE-2-LORSA-16K-K64
    4. 79
    Prev
    Next
    INDEX
    Explanations

    say ancient empires

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

    No Comments

    Negative Logits
     Melbourne
    -22.13
    澳
    -21.00
     Mueller
    -20.63
     Hungarian
    -20.00
     Schwe
    -19.88
     Brisbane
    -19.38
     Swedish
    -19.13
    芬兰
    -18.88
    晋江
    -18.50
    bö
    -18.13
    POSITIVE LOGITS
    秦国
    26.38
    (bc
    21.38
    秦
    20.88
    咸阳
    20.75
     Babylon
    20.63
    _bc
    20.00
     Persian
    19.88
    嫪
    19.75
     Iran
    19.38
    _BC
    19.13
    Activations Density 0.110%

    No Known Activations