© 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. 15752
    Prev
    Next
    INDEX
    Explanations

    say "expansion"

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

    No Comments

    Negative Logits
    泣
    -16.25
    鲫
    -16.00
    reeze
    -15.25
    cip
    -15.19
     cashier
    -14.19
    abei
    -13.75
     neckline
    -13.69
    翻身
    -13.56
    寨
    -13.50
    _BAL
    -13.44
    POSITIVE LOGITS
    扩展
    71.50
     extension
    64.50
     extensions
    62.75
     expansion
    59.00
     Extension
    58.50
     expansions
    58.25
    扩张
    57.75
    extension
    57.75
     Extensions
    57.25
    Extension
    56.50
    Activations Density 0.506%

    No Known Activations