© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 566
    Prev
    Next
    INDEX
    Explanations

    say document sections

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

    No Comments

    Negative Logits
     KA
    -18.38
    .sheet
    -18.00
    .za
    -16.88
    沙
    -16.88
     Kw
    -16.88
    zag
    -16.88
    quat
    -16.38
    ção
    -16.38
    spiel
    -16.13
     KM
    -16.00
    POSITIVE LOGITS
     Tur
    15.94
    溥
    15.56
     AS
    15.25
     AG
    15.19
     Denver
    15.13
     Buckley
    15.06
     AP
    14.81
    AT
    14.75
     AC
    14.13
     Oklahoma
    13.94
    Activations Density 0.091%

    No Known Activations