© 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. 15624
    Prev
    Next
    INDEX
    Explanations

    author citations

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

    No Comments

    Negative Logits
    囡
    -21.75
    圜
    -19.13
    邝
    -18.50
    鱿
    -18.38
    炯
    -17.75
    碉
    -17.75
    壕
    -17.50
    猴
    -16.88
     MCP
    -16.63
     cooker
    -16.38
    POSITIVE LOGITS
    罗斯
    33.00
     WS
    32.50
    萧
    31.63
    (rs
    30.75
     TAS
    30.50
    oss
    30.25
    rs
    29.88
    RS
    29.50
     HS
    28.88
    	rs
    28.88
    Activations Density 6.105%

    No Known Activations