© 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. 14934
    Prev
    Next
    INDEX
    Explanations

    say six

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    ooks
    -16.13
    kus
    -14.88
    rys
    -14.75
    edly
    -14.00
    睹
    -13.88
    八年
    -13.63
    okus
    -13.63
    下游
    -13.38
     excl
    -13.38
    uly
    -13.38
    POSITIVE LOGITS
    6
    41.75
     six
    41.25
     sixth
    37.75
    六个
    36.75
    -six
    36.00
    six
    35.25
     Six
    34.75
    ６
    34.50
     SIX
    33.75
     Sixth
    33.50
    Activations Density 0.699%

    No Known Activations