© 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. 188
    Prev
    Next
    INDEX
    Explanations

    say Chinese place names

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

    No Comments

    Negative Logits
     Snapchat
    -23.25
    Instagram
    -23.00
    WhatsApp
    -21.75
     Instagram
    -21.38
     cryptocurrency
    -21.13
    主播
    -20.75
    Phones
    -20.75
    俄乌
    -20.63
    口罩
    -20.63
    COVID
    -20.50
    POSITIVE LOGITS
    新农村
    20.38
    宜昌
    16.63
    .cms
    16.50
    武汉
    16.25
    梅州
    16.13
    十堰
    16.13
    湖北省
    15.38
    亳
    14.69
    农村
    14.44
    无锡
    14.44
    Activations Density 0.395%

    No Known Activations