© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 16138
    Prev
    Next
    INDEX
    Explanations

    say "Web"

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

    No Comments

    Negative Logits
    胡萝卜
    -23.13
    菲
    -20.13
    SSI
    -19.50
    腓
    -19.13
     raspberry
    -18.75
    包子
    -18.38
    .pi
    -18.00
    造船
    -17.88
     ROM
    -17.50
     Tyson
    -17.50
    POSITIVE LOGITS
    conc
    25.38
     Conc
    22.25
     conc
    22.25
    con
    22.00
    -con
    21.75
     coc
    21.63
    kon
    20.38
    -Con
    20.38
    .Flush
    20.25
    Con
    19.88
    Activations Density 0.703%

    No Known Activations