© 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. 2774
    Prev
    Next
    INDEX
    Explanations

    say "Gil"

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

    No Comments

    Negative Logits
     Ref
    -18.63
     ref
    -18.13
    $req
    -17.75
    (ref
    -17.75
    ref
    -17.38
    .Ref
    -16.63
    (em
    -16.50
     mutate
    -16.50
    _Ref
    -16.38
     refute
    -16.38
    POSITIVE LOGITS
     Gil
    62.75
    Gil
    57.00
    代
    51.00
     gen
    37.50
    gil
    37.50
    (gen
    37.00
     GEN
    36.75
     Gen
    35.75
    GEN
    35.00
     gener
    33.50
    Activations Density 0.036%

    No Known Activations