© 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. 16132
    Prev
    Next
    INDEX
    Explanations

    say "br"

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

    No Comments

    Negative Logits
     Fiona
    -24.13
    佤
    -23.50
    asha
    -21.63
    苕
    -21.25
     Roo
    -21.25
     Sok
    -20.63
     Wool
    -20.50
    桃花
    -20.00
     Kodi
    -19.88
     Terry
    -19.75
    POSITIVE LOGITS
    (br
    25.25
    -br
    24.63
    br
    24.50
    abr
    24.38
    _br
    23.25
    Br
    22.75
    bras
    22.63
    .br
    22.25
    brate
    22.00
    .Br
    21.75
    Activations Density 0.311%

    No Known Activations