© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1136
    Prev
    Next
    INDEX
    Explanations

    say "engine"

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

    No Comments

    Negative Logits
    Mac
    -57.75
    MAC
    -57.25
     Mac
    -56.25
     mac
    -56.00
    mac
    -54.50
     MAC
    -53.75
    _mac
    -53.00
    /mac
    -50.25
     macro
    -46.50
    (mac
    -46.50
    POSITIVE LOGITS
    _engine
    21.00
    engine
    20.88
     engine
    20.50
    发动机
    20.50
    引擎
    20.25
     ENGINE
    20.13
    ENGINE
    19.88
     Engine
    19.75
    Engine
    19.63
    -engine
    19.50
    Activations Density 0.167%

    No Known Activations