© 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. 59
    Prev
    Next
    INDEX
    Explanations

    say political titles

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

    No Comments

    Negative Logits
    achusetts
    -17.75
     Spirits
    -17.75
     Corps
    -17.75
    (visitor
    -17.13
    Java
    -17.13
     Connecticut
    -17.00
    天国
    -17.00
    营销
    -16.88
    HORT
    -16.25
     spectator
    -16.25
    POSITIVE LOGITS
     MP
    18.38
    党内
    16.88
    首相
    16.75
     PM
    15.81
     Labour
    15.31
    蹇
    15.31
     NDP
    15.13
     TPP
    14.94
    蛤
    14.88
     Trudeau
    14.69
    Activations Density 0.122%

    No Known Activations