© 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. 2188
    Prev
    Next
    INDEX
    Explanations

    Gilbert

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

    No Comments

    Negative Logits
     cur
    -22.00
    .cur
    -22.00
    cur
    -22.00
    _cur
    -21.25
    Cur
    -20.50
     dir
    -19.75
    (cur
    -19.38
    Curr
    -19.38
     Cur
    -19.00
     recurs
    -18.88
    POSITIVE LOGITS
     Gilbert
    43.50
     tab
    25.88
    tab
    25.75
     Tab
    25.38
    Tab
    25.38
    cert
    24.75
     Cert
    23.50
    CERT
    23.50
     cert
    23.00
     Herbert
    23.00
    Activations Density 0.034%

    No Known Activations