© 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. 2126
    Prev
    Next
    INDEX
    Explanations

    say "Margaret"

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

    No Comments

    Negative Logits
     Rec
    -18.63
    -btn
    -18.38
     btn
    -17.50
    _vec
    -17.13
     Btn
    -16.75
    ortho
    -16.50
    (btn
    -16.25
    .btn
    -15.94
    _sec
    -15.94
     chk
    -15.81
    POSITIVE LOGITS
    Marg
    54.00
     Margaret
    48.25
     Marg
    43.00
     marg
    42.25
     marginal
    38.75
     margin
    36.25
     margins
    34.25
     Margin
    33.25
    margin
    31.88
    (segment
    30.00
    Activations Density 0.027%

    No Known Activations