© 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
    2. Qwen3-1.7B
    3. 27-LLAMASCOPE-2-LORSA-16K-K64
    4. 16269
    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
     Ridley
    -29.50
    虹桥
    -24.00
    祁
    -23.38
     Benton
    -22.75
     Eid
    -22.75
     Kaw
    -22.25
     ISIS
    -22.13
     Salisbury
    -21.88
     Lena
    -21.63
     Sutton
    -21.13
    POSITIVE LOGITS
    浆
    22.63
    柊
    22.50
     Marino
    21.50
     Frankie
    21.38
    osp
    20.63
    (hWnd
    20.25
    桢
    20.13
     Tango
    20.00
     Vista
    19.63
     Clara
    19.63
    Activations Density 4.923%

    No Known Activations