© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1839
    Prev
    Next
    INDEX
    Explanations

    jade

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

    No Comments

    Negative Logits
    玉
    -30.75
    玉石
    -27.13
     diamond
    -25.13
     Diamonds
    -23.88
     diamonds
    -23.25
    diamond
    -22.75
    Diamond
    -21.50
     ruby
    -21.13
    钻石
    -21.00
    Ruby
    -19.63
    POSITIVE LOGITS
    枪
    17.13
    江西省
    16.63
    江西
    15.81
     Edu
    15.75
    socket
    15.44
    绍兴
    15.19
    ilot
    14.94
    精神
    14.88
    edin
    14.81
    eking
    14.56
    Activations Density 0.109%

    No Known Activations