© 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. 13996
    Prev
    Next
    INDEX
    Explanations

    say "query"

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

    No Comments

    Negative Logits
    生产能力
    -21.25
    觀察
    -19.38
    观察
    -19.38
     observation
    -19.13
     observations
    -18.75
     Tour
    -18.75
    觀
    -18.75
     comparison
    -18.50
     compares
    -18.50
     comparisons
    -18.13
    POSITIVE LOGITS
     query
    17.75
    查询
    16.50
    ervlet
    16.13
     policies
    16.00
     Query
    15.56
     fields
    15.50
    Scheme
    15.44
    (interp
    15.44
    query
    15.38
    (fields
    15.25
    Activations Density 0.815%

    No Known Activations