© 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. 15657
    Prev
    Next
    INDEX
    Explanations

    N/A

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

    No Comments

    Negative Logits
     Ced
    -23.75
     Bethlehem
    -21.50
     Mansion
    -20.63
    枉
    -20.25
    Ted
    -20.25
    Stra
    -20.13
    枳
    -19.88
     TED
    -19.75
    绛
    -19.50
    橙
    -19.38
    POSITIVE LOGITS
    刘海
    21.13
     dataIndex
    19.38
    配资
    19.25
    toi
    19.13
    税费
    18.88
     indexer
    18.88
    蚶
    18.75
    巴基
    18.63
     Carly
    18.38
    灣
    18.38
    Activations Density 4.044%

    No Known Activations