© 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. 14050
    Prev
    Next
    INDEX
    Explanations

    say engine words

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

    No Comments

    Negative Logits
    .FILL
    -18.38
    防线
    -18.25
    MethodInfo
    -18.13
    庆典
    -18.00
    creenshot
    -17.88
    methodName
    -17.38
    (Method
    -17.25
    .getMethod
    -17.13
    专卖店
    -16.75
    便利店
    -16.63
    POSITIVE LOGITS
    发动机
    28.25
     engine
    28.25
     engines
    27.63
    引擎
    26.13
    (engine
    23.25
     Engine
    22.50
    	engine
    21.75
     Engines
    21.50
     двигат
    21.13
    驱动
    21.00
    Activations Density 0.147%

    No Known Activations