© 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. 15597
    Prev
    Next
    INDEX
    Explanations

    say "est"

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

    No Comments

    Negative Logits
    yan
    -21.88
     Yan
    -21.75
    blade
    -20.75
    ible
    -19.38
     Fior
    -19.13
     snaps
    -18.63
    po
    -18.63
    shan
    -18.38
    IBLE
    -18.00
     yan
    -17.75
    POSITIVE LOGITS
     Wash
    19.13
    WSC
    18.88
     Essex
    18.88
    estate
    17.88
     Westminster
    17.75
     Washing
    17.63
    濯
    17.63
     washed
    17.63
     Cristina
    17.13
     CST
    17.00
    Activations Density 0.001%

    No Known Activations