© 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. 13916
    Prev
    Next
    INDEX
    Explanations

    say "scene"

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

    No Comments

    Negative Logits
     Operation
    -29.88
     operation
    -29.75
    Operation
    -27.63
     operations
    -26.88
    operation
    -26.25
    -operation
    -25.88
     oper
    -25.63
     OPERATION
    -25.63
    OPER
    -25.38
     Oper
    -25.25
    POSITIVE LOGITS
    推
    18.50
    	scene
    17.88
    .scenes
    17.75
    _SCENE
    17.38
    scenes
    17.13
     scenes
    17.00
    抽取
    16.75
    _scene
    16.50
     Scene
    16.13
    scene
    16.13
    Activations Density 0.666%

    No Known Activations