© 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. 3032
    Prev
    Next
    INDEX
    Explanations

    say "释"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    det
    -20.50
    DIG
    -19.88
    模拟
    -19.75
    (per
    -18.50
    (det
    -17.88
     DIG
    -17.75
     Mum
    -17.38
     analog
    -17.13
     sim
    -17.13
     perm
    -16.75
    POSITIVE LOGITS
    释
    32.00
    釋
    21.63
     ER
    21.63
     serial
    21.38
     er
    21.13
     Serial
    21.00
     Er
    19.88
    erm
    19.88
     des
    19.25
    Serial
    19.13
    Activations Density 0.072%

    No Known Activations