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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15834
    Prev
    Next
    INDEX
    Explanations

    say surnames

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

    No Comments

    Negative Logits
    ubuntu
    -17.88
     ubuntu
    -17.75
    Ubuntu
    -17.00
    /ubuntu
    -16.88
    大城市
    -16.50
     Ubuntu
    -15.88
    .Region
    -15.13
    元旦
    -15.06
     Epid
    -14.63
     signin
    -14.63
    POSITIVE LOGITS
     McL
    25.88
     McM
    24.38
    Williams
    23.38
     McInt
    23.13
     McGu
    22.25
     McConnell
    21.63
     Williams
    21.50
     Sullivan
    21.25
     McN
    21.25
    Mc
    21.13
    Activations Density 0.367%

    No Known Activations