© 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. 16356
    Prev
    Next
    INDEX
    Explanations

    non‑ASCII glyphs

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

    No Comments

    Negative Logits
    ZE
    -32.00
    QE
    -32.00
     SCE
    -32.00
     QE
    -31.25
    NES
    -29.63
    CEE
    -29.50
    鹿
    -29.25
     Greene
    -29.13
    OE
    -28.50
    enne
    -28.13
    POSITIVE LOGITS
    枭
    20.63
     Rubin
    19.63
     Thornton
    19.00
    卣
    17.88
    lington
    17.88
     Shaft
    17.38
    毓
    17.25
    (Parser
    17.00
    扬州
    17.00
     Salvador
    16.13
    Activations Density 4.184%

    No Known Activations