© 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. 292
    Prev
    Next
    INDEX
    Explanations

    say "two-letter codes"

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

    No Comments

    Negative Logits
     Leeds
    -17.50
     Baghdad
    -16.38
    西湖
    -16.13
     Kolkata
    -15.88
     Yorkshire
    -15.88
    京都
    -15.56
     London
    -15.00
     Suffolk
    -14.81
    .hamcrest
    -14.00
    琢
    -13.81
    POSITIVE LOGITS
     CN
    63.00
     PN
    60.50
     GN
    59.75
    CN
    59.75
     TN
    59.50
     FN
    58.50
     BN
    57.75
     LN
    56.25
    (cn
    56.00
    TN
    55.75
    Activations Density 0.480%

    No Known Activations