© 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. 100
    Prev
    Next
    INDEX
    Explanations

    say Tibet

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

    No Comments

    Negative Logits
    潜艇
    -19.50
    抗生素
    -18.13
    Nike
    -17.88
     sulfate
    -17.00
     Kens
    -17.00
    COPE
    -16.88
    饲料
    -16.88
    reas
    -16.88
     Crypto
    -16.75
    anime
    -16.75
    POSITIVE LOGITS
     Tibetan
    21.00
    西藏
    18.25
     Tibet
    17.50
     voter
    17.25
    ong
    16.88
    民主党
    16.25
    邛
    16.00
     electoral
    15.69
     Parl
    15.56
     voters
    15.44
    Activations Density 0.093%

    No Known Activations