© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 3299
    Prev
    Next
    INDEX
    Explanations

    say liquid

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    range
    -19.13
     Range
    -17.63
     COMPANY
    -16.88
    lob
    -16.75
    _Table
    -16.63
    _RANGE
    -16.13
    IMAGE
    -16.13
    家公司
    -15.88
     Pty
    -15.81
    梵
    -15.44
    POSITIVE LOGITS
    液
    32.50
     liquid
    24.88
    液体
    23.75
    liquid
    20.63
     Liquid
    19.25
    Liquid
    19.00
    溶液
    16.75
    叶
    16.38
     fluid
    15.44
     TSR
    15.19
    Activations Density 0.029%

    No Known Activations