© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14166
    Prev
    Next
    INDEX
    Explanations

    say "event"

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

    No Comments

    Negative Logits
     forms
    -32.75
     form
    -32.25
     Forms
    -31.50
    _forms
    -30.50
     Form
    -29.63
    forms
    -29.63
    Forms
    -29.25
    _form
    -28.50
     forme
    -28.38
    Form
    -28.00
    POSITIVE LOGITS
    事件
    17.75
     event
    16.13
    イベント
    15.88
    ataloader
    15.81
     SceneManager
    15.81
    Event
    15.56
    行为
    15.56
     событи
    15.50
     events
    15.25
    events
    15.19
    Activations Density 0.644%

    No Known Activations