© 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. 14913
    Prev
    Next
    INDEX
    Explanations

    code syntax

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

    No Comments

    Negative Logits
    rms
    -19.50
     RMS
    -19.25
    芮
    -19.00
     rms
    -18.88
    úa
    -17.75
     экс
    -17.50
    OOM
    -17.50
    rum
    -17.13
    xmm
    -17.00
    虬
    -16.88
    POSITIVE LOGITS
     Bannon
    20.75
    洋葱
    20.13
     Gunn
    17.88
     Sanchez
    16.88
     tee
    16.63
    (TokenType
    16.63
    inz
    16.50
    tee
    16.50
     Odin
    16.50
     wolf
    16.38
    Activations Density 1.102%

    No Known Activations