© 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. 14622
    Prev
    Next
    INDEX
    Explanations

    say three-letter abbreviations

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

    No Comments

    Negative Logits
    洋葱
    -21.00
     Bannon
    -20.75
     Gunn
    -18.63
     Sanchez
    -17.38
     Onion
    -17.25
    (TokenType
    -17.13
     Odin
    -17.13
     TokenType
    -16.75
     tee
    -16.75
    tee
    -16.63
    POSITIVE LOGITS
    rms
    19.75
     RMS
    19.13
     rms
    18.88
    芮
    18.50
    OOM
    17.13
     экс
    16.50
    úa
    16.38
    xmm
    16.25
    rum
    16.13
    ilia
    16.13
    Activations Density 0.943%

    No Known Activations