© 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. 14953
    Prev
    Next
    INDEX
    Explanations

    say "2"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    ностей
    -22.00
    南阳
    -20.00
    萩
    -19.63
    EMS
    -19.50
    holm
    -19.00
     Nicola
    -18.50
    HAND
    -18.38
    RAFT
    -18.38
    (PDO
    -18.38
    (DataType
    -17.88
    POSITIVE LOGITS
    坞
    16.38
     le
    15.81
    ware
    15.50
     ware
    15.00
    碓
    14.75
     Plate
    14.50
     plateau
    14.44
    iling
    14.19
     plate
    13.88
    acre
    13.88
    Activations Density 0.015%

    No Known Activations