© 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. 15971
    Prev
    Next
    INDEX
    Explanations

    say "extent"

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

    No Comments

    Negative Logits
    ahlen
    -17.88
    ось
    -16.13
    ahl
    -15.88
    .snap
    -15.81
    qli
    -15.50
    军工
    -15.06
    vio
    -14.94
    bindValue
    -14.75
     wire
    -14.69
    kip
    -14.06
    POSITIVE LOGITS
     ext
    22.25
     extend
    22.25
     extending
    21.13
     extended
    21.13
    _extend
    20.88
    _degree
    20.75
    .Ext
    20.63
    extended
    20.13
     Ext
    20.00
    .extend
    19.88
    Activations Density 0.016%

    No Known Activations