© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14823
    Prev
    Next
    INDEX
    Explanations

    say grass

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

    No Comments

    Negative Logits
     catalogue
    -17.63
    党组
    -17.13
    listen
    -16.38
    Listening
    -16.25
    sink
    -16.00
    (anchor
    -15.88
    /Branch
    -15.38
    .Lib
    -15.19
    支
    -15.19
     Catalog
    -15.19
    POSITIVE LOGITS
    剑
    19.50
    劍
    19.50
    草
    17.50
    草地
    17.38
     Lawn
    17.38
     Blades
    17.25
     grass
    17.25
    grass
    16.25
    草坪
    16.25
     lawn
    16.13
    Activations Density 0.118%

    No Known Activations