© 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. 15524
    Prev
    Next
    INDEX
    Explanations

    author surname

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

    No Comments

    Negative Logits
     Spokane
    -20.88
    开发区
    -19.25
    LayoutPanel
    -18.75
    ropolitan
    -18.63
    acy
    -18.38
     Westbrook
    -18.25
     Terrace
    -18.13
    展区
    -17.88
     adc
    -17.75
    郊
    -17.63
    POSITIVE LOGITS
    拔
    19.38
    结晶
    18.13
    pis
    17.50
     boiled
    17.13
    质押
    17.00
    煮
    16.88
     chim
    16.63
     deut
    16.00
     nailed
    16.00
    .PI
    16.00
    Activations Density 0.533%

    No Known Activations