© 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. 15359
    Prev
    Next
    INDEX
    Explanations

    [#include] => [#include]

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

    No Comments

    Negative Logits
    lea
    -18.13
    …”
    -17.75
    蛮
    -17.50
    谌
    -17.25
     Clem
    -17.00
    xab
    -16.50
     Sachs
    -16.13
    …”↵↵
    -16.13
    lek
    -16.13
    白马
    -15.75
    POSITIVE LOGITS
    NES
    17.13
     Lilly
    16.38
    _MPI
    16.13
    .Footer
    16.13
    /Runtime
    16.13
    笼
    16.00
    summ
    15.88
    NR
    15.81
    isArray
    15.63
     yyn
    15.56
    Activations Density 0.007%

    No Known Activations