© 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. 15663
    Prev
    Next
    INDEX
    Explanations

    [flex] => [flex]

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

    No Comments

    Negative Logits
    降
    -16.25
     degraded
    -15.63
     infl
    -15.13
     preval
    -15.06
    漏
    -14.69
     Co
    -14.69
    敝
    -14.56
    Leaks
    -14.50
    (infile
    -14.38
    褪
    -14.31
    POSITIVE LOGITS
     Bunny
    22.00
     bunny
    21.00
    iger
    20.88
     Mick
    19.88
    burger
    19.63
     Mickey
    19.50
     Zucker
    19.25
     Booker
    19.13
     cakes
    18.38
     cake
    18.25
    Activations Density 0.293%

    No Known Activations