© 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. 15527
    Prev
    Next
    INDEX
    Explanations

    br

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

    No Comments

    Negative Logits
    Wal
    -20.63
     wal
    -20.00
     Wal
    -19.75
     scor
    -19.63
     Shawn
    -19.13
    邬
    -18.88
    REA
    -18.25
     sch
    -17.50
     Savannah
    -17.38
     gam
    -17.00
    POSITIVE LOGITS
    ltr
    19.13
     ATF
    18.38
    lest
    17.88
     Bridges
    17.75
    tek
    17.63
    fonts
    17.50
    mlx
    17.38
    istle
    17.13
     Bridge
    16.88
    大桥
    16.75
    Activations Density 0.140%

    No Known Activations