© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 825
    Prev
    Next
    INDEX
    Explanations

    say "jazz"

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

    No Comments

    Negative Logits
     Tasmania
    -19.75
    辙
    -19.38
    TextNode
    -18.63
     Tolkien
    -18.38
    decrypt
    -18.13
    olith
    -18.00
    西宁
    -17.50
    隗
    -17.50
     Tamil
    -17.38
     Cupertino
    -17.38
    POSITIVE LOGITS
     Harlem
    29.00
     Chicago
    24.50
    在广州
    23.38
    Chicago
    22.88
    广州市
    22.38
    粤
    22.00
    爵士
    22.00
    芝加哥
    21.63
     jazz
    21.63
     African
    21.13
    Activations Density 0.075%

    No Known Activations