© 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. 15520
    Prev
    Next
    INDEX
    Explanations

    say "suffixes"

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

    No Comments

    Negative Logits
     Ezra
    -26.88
    yre
    -25.75
     Bret
    -24.13
     TRE
    -23.75
     Braun
    -23.25
     Blair
    -23.25
    aire
    -23.00
     Clair
    -23.00
    andre
    -22.75
     TOUR
    -22.38
    POSITIVE LOGITS
     ROC
    28.63
    ROC
    27.25
    ϱ
    22.88
     Alic
    22.38
    .ping
    21.88
    桔
    21.88
    _ping
    21.63
     Hitch
    21.50
    璜
    21.25
     ping
    20.88
    Activations Density 5.848%

    No Known Activations