© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14769
    Prev
    Next
    INDEX
    Explanations

    say "H"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    H
    -44.75
     H
    -44.50
     h
    -42.75
    h
    -40.25
    _h
    -39.75
    -h
    -38.00
    赵
    -35.75
    :H
    -35.00
    .h
    -34.25
    [h
    -33.75
    POSITIVE LOGITS
    fold
    14.13
    上班
    14.00
    PTY
    13.81
    薪
    13.56
    beg
    13.06
    本领
    12.75
    ken
    12.69
    优越
    12.50
    _claim
    12.31
    キャン
    12.25
    Activations Density 0.473%

    No Known Activations