© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15680
    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
     Willow
    -25.50
     Mojo
    -24.25
     mojo
    -23.38
    蕉
    -23.13
     Brady
    -22.00
     banana
    -21.88
    香蕉
    -21.63
    芗
    -21.13
    ilar
    -20.63
     Mush
    -20.25
    POSITIVE LOGITS
    Knight
    20.88
     Falk
    20.63
    �
    20.50
    bnb
    20.38
    ockets
    20.13
     Elli
    19.88
    орт
    19.88
    Wolf
    19.50
     Wolf
    19.38
     Montgomery
    19.38
    Activations Density 4.494%

    No Known Activations