© 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. 1209
    Prev
    Next
    INDEX
    Explanations

    do not say letters

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     letter
    -56.25
     letters
    -56.00
     Letters
    -52.00
     Letter
    -51.00
    letter
    -51.00
    Letter
    -50.75
     LETTER
    -50.00
    字母
    -49.25
    letters
    -48.50
    _letter
    -47.75
    POSITIVE LOGITS
    扶贫
    14.88
    orio
    14.25
    雲
    14.13
    _cuda
    14.06
     cloud
    13.75
    IOC
    13.69
    云计算
    13.69
    VO
    13.69
    NK
    13.63
     Pacific
    13.56
    Activations Density 0.070%

    No Known Activations