© 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. 502
    Prev
    Next
    INDEX
    Explanations

    chat delimiters

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

    No Comments

    Negative Logits
     Japanese
    -26.25
     Icelandic
    -25.25
    Japanese
    -24.50
     Indonesian
    -24.38
     Iceland
    -21.63
     Japan
    -21.38
    Japan
    -21.25
    日本
    -21.25
     japanese
    -21.25
     Hiro
    -20.88
    POSITIVE LOGITS
     AB
    22.38
    ABB
    22.00
    BB
    21.88
     UB
    21.38
    AB
    21.25
    AZ
    21.00
    澧
    20.88
     BB
    19.75
     AL
    19.50
     AZ
    19.25
    Activations Density 0.119%

    No Known Activations