© 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. 15780
    Prev
    Next
    INDEX
    Explanations

    numbers

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

    No Comments

    Negative Logits
    8
    -48.25
    八
    -46.75
     eight
    -45.75
     eighty
    -40.75
    八个
    -40.50
    ８
    -40.00
     Eight
    -39.50
     eighth
    -39.25
    eight
    -37.50
    -eight
    -37.00
    POSITIVE LOGITS
     SECURITY
    14.63
    爵士
    14.31
    ValidationError
    14.25
    丕
    14.19
     piel
    14.00
     plagiar
    13.88
     Plymouth
    13.88
     đại
    13.69
    plates
    13.69
     security
    13.69
    Activations Density 1.988%

    No Known Activations