© 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. 439
    Prev
    Next
    INDEX
    Explanations

    say "letter sequences"

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

    No Comments

    Negative Logits
     Russian
    -31.50
     Russians
    -31.13
    俄罗斯
    -30.25
    俄
    -28.88
     Russia
    -28.13
    Russian
    -28.13
     Putin
    -27.25
    俄军
    -25.13
     Moscow
    -25.00
    普京
    -24.88
    POSITIVE LOGITS
     XYZ
    53.50
     ABC
    53.50
     xyz
    50.50
    xyz
    49.75
     abc
    49.50
    ABC
    49.25
    XYZ
    49.00
    abc
    46.00
    (xy
    45.50
     xy
    45.25
    Activations Density 0.447%

    No Known Activations