© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14634
    Prev
    Next
    INDEX
    Explanations

    say numbers

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

    No Comments

    Negative Logits
     glam
    -19.88
    alam
    -19.25
    al
    -19.25
     Haley
    -19.13
     Walton
    -18.25
    hal
    -17.88
    aney
    -17.63
    バン
    -17.50
     manic
    -17.50
    alu
    -17.50
    POSITIVE LOGITS
     Burgess
    21.00
     Musk
    19.75
    ERM
    19.50
    hurst
    19.00
    رش
    18.63
     Dart
    18.50
    erti
    18.38
     MART
    18.38
    irts
    18.25
    曙
    18.25
    Activations Density 1.109%

    No Known Activations