© 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. 16355
    Prev
    Next
    INDEX
    Explanations

    say "contraction"

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

    No Comments

    Negative Logits
    山寨
    -19.88
     Maver
    -18.63
    cpy
    -17.50
    山水
    -17.38
    ��索
    -17.13
    登入
    -16.88
    DFS
    -16.50
    öst
    -16.50
    山顶
    -16.38
    酪
    -16.38
    POSITIVE LOGITS
     contraction
    31.88
     contracts
    31.63
    收缩
    31.13
     contract
    30.25
     expansion
    30.13
     expand
    30.13
    膨胀
    29.38
     expanding
    29.13
    contract
    28.75
    扩张
    28.63
    Activations Density 0.208%

    No Known Activations