© 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. 29
    Prev
    Next
    INDEX
    Explanations

    say city names

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

    No Comments

    Negative Logits
     Dante
    -19.38
     Weber
    -17.63
     Isaac
    -17.50
     Antonio
    -17.25
     Henrik
    -16.88
    荀
    -16.63
     Hardy
    -16.63
     Jorge
    -16.50
     Eduardo
    -16.50
     Giovanni
    -16.13
    POSITIVE LOGITS
     Atlanta
    20.88
    Atlanta
    19.38
     NYC
    19.13
    华人
    18.88
    在北京
    18.75
    ruk
    18.13
    北京市
    17.88
     Beijing
    17.75
    hte
    17.38
    BCM
    17.25
    Activations Density 0.172%

    No Known Activations