© 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. 2306
    Prev
    Next
    INDEX
    Explanations

    Charlie

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

    No Comments

    Negative Logits
     ctx
    -20.13
    ctx
    -19.88
     Sem
    -19.63
    Sem
    -19.38
    (ctx
    -19.13
    .ctx
    -18.75
     Mer
    -18.63
     Mir
    -18.38
     mer
    -17.50
    _cur
    -16.88
    POSITIVE LOGITS
     Charlie
    43.50
    Charlie
    42.75
    (eq
    22.00
     Melanie
    20.38
     poly
    20.13
    汤
    19.25
     Pete
    18.63
     Jessie
    18.38
    (poly
    18.00
    忘记
    17.63
    Activations Density 0.031%

    No Known Activations