© 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. 15943
    Prev
    Next
    INDEX
    Explanations

    say "att" words

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

    No Comments

    Negative Logits
     Ale
    -19.25
     polit
    -18.75
     Britt
    -18.25
     duk
    -18.00
     política
    -17.88
    アル
    -17.50
     politique
    -17.38
    ARA
    -17.25
    ara
    -17.13
     piracy
    -17.13
    POSITIVE LOGITS
    _ATT
    20.00
    atts
    19.63
     ATT
    19.00
    att
    18.38
     attended
    18.38
     attends
    18.13
    (att
    18.13
    attended
    17.50
    ATT
    17.38
    _Att
    17.38
    Activations Density 0.601%

    No Known Activations