© 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. 682
    Prev
    Next
    INDEX
    Explanations

    say surnames

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

    No Comments

    Negative Logits
    欧元
    -19.75
    Euro
    -18.75
    _DF
    -18.50
     Ukrain
    -18.50
    scala
    -18.50
    是韩国
    -18.25
     DF
    -18.13
     euro
    -18.00
     Ghana
    -17.88
     Africans
    -17.75
    POSITIVE LOGITS
     Johnson
    41.75
    Johnson
    39.75
     Hughes
    39.50
     Smith
    38.50
    Smith
    37.50
     Anderson
    37.25
     McKay
    37.25
    Anderson
    36.75
     Goodman
    36.75
     Wilson
    36.50
    Activations Density 1.069%

    No Known Activations