© 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. 15863
    Prev
    Next
    INDEX
    Explanations

    say fire

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

    No Comments

    Negative Logits
     GPI
    -21.00
    _mex
    -20.13
     gi
    -18.88
    _cg
    -18.88
     dp
    -18.63
    (gp
    -18.50
     MEP
    -18.38
    enet
    -18.38
    $wp
    -18.25
    ,ep
    -18.00
    POSITIVE LOGITS
    8
    20.25
     burn
    20.00
     flame
    19.13
    烧
    19.00
    火烧
    18.75
    9
    17.75
    烈
    17.50
    火焰
    17.50
    7
    17.38
     blaze
    17.38
    Activations Density 0.071%

    No Known Activations