© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 815
    Prev
    Next
    INDEX
    Explanations

    say "famous leaders"

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

    No Comments

    Negative Logits
     Cs
    -22.25
    ds
    -20.00
     ds
    -20.00
    (ds
    -19.25
     uw
    -19.00
    Cs
    -18.88
    KC
    -18.63
    /cs
    -18.38
     kc
    -18.38
    kc
    -17.88
    POSITIVE LOGITS
     Mandela
    37.75
     Tamil
    22.88
     Gandhi
    20.00
     Rhodes
    19.38
     NDP
    19.38
    南阳
    19.13
    �
    19.13
    温州
    18.63
    鞍山
    18.25
     Nelson
    17.88
    Activations Density 0.013%

    No Known Activations