© 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. 13897
    Prev
    Next
    INDEX
    Explanations

    say draw

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

    No Comments

    Negative Logits
     input
    -21.13
    Input
    -20.75
     Input
    -20.38
    input
    -19.88
    输入
    -19.63
    _input
    -19.25
    .input
    -19.00
     INPUT
    -18.00
    _Input
    -17.88
    =input
    -17.75
    POSITIVE LOGITS
     drawings
    21.38
     drawing
    18.00
    	draw
    17.63
     draw
    17.25
     sketches
    16.88
     draws
    16.75
    Drawing
    16.63
    驱动
    16.38
    (draw
    16.25
     Drawing
    16.13
    Activations Density 0.778%

    No Known Activations