© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 2778
    Prev
    Next
    INDEX
    Explanations

    say "Jun"

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

    No Comments

    Negative Logits
     Serial
    -22.13
     serial
    -20.50
    leg
    -19.50
    _SERIAL
    -19.25
    _serial
    -19.25
    serializer
    -19.25
    Serial
    -19.13
    serial
    -19.00
    .serial
    -18.88
    _serializer
    -18.00
    POSITIVE LOGITS
     Jun
    48.00
    Jun
    46.25
     jun
    35.50
     ctx
    34.25
    jun
    33.00
     Jul
    32.75
    (ctx
    31.63
    ctx
    30.00
     δ
    28.38
    Ctx
    28.00
    Activations Density 0.037%

    No Known Activations