© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 142
    Prev
    Next
    INDEX
    Explanations

    say prefixes

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

    No Comments

    Negative Logits
     Cv
    -20.63
     Cairo
    -19.75
    荆州
    -19.25
     Cs
    -18.00
    南沙
    -17.88
     Php
    -17.63
     CV
    -17.63
     CZ
    -17.50
     Laguna
    -17.50
     Dh
    -17.25
    POSITIVE LOGITS
     wy
    22.38
     ky
    22.38
    (nx
    17.75
     kim
    17.50
     wer
    17.50
    .fx
    17.00
     wol
    16.88
    yon
    16.50
     kir
    16.50
    wel
    16.38
    Activations Density 0.037%

    No Known Activations