© 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. 914
    Prev
    Next
    INDEX
    Explanations

    say countries

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

    No Comments

    Negative Logits
     EB
    -23.38
    XB
    -20.88
    EB
    -20.75
    (ib
    -20.38
     gib
    -20.38
    xab
    -20.25
    (pb
    -19.75
     ib
    -19.63
    xAB
    -19.63
     xb
    -19.00
    POSITIVE LOGITS
     Finnish
    27.38
     Nigerian
    27.25
     Thai
    26.63
     Ghana
    26.00
    枣庄
    25.75
     Uganda
    25.50
    泰国
    25.38
    楚
    25.25
     Thailand
    25.13
     mongoose
    25.00
    Activations Density 0.108%

    No Known Activations