© 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. 15859
    Prev
    Next
    INDEX
    Explanations

    say "O" tokens

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

    No Comments

    Negative Logits
    蕨
    -14.38
    endon
    -13.94
    蚬
    -13.88
    ilon
    -13.88
    endas
    -13.75
    텔
    -13.44
    镞
    -13.38
     fern
    -13.25
    .Suppress
    -12.88
    Thunk
    -12.81
    POSITIVE LOGITS
    奧
    47.25
    奥
    46.25
    -O
    46.00
     OA
    44.00
     OM
    43.25
    /O
    42.75
     OC
    42.25
    -o
    42.00
    _O
    41.50
    .O
    40.50
    Activations Density 6.309%

    No Known Activations