© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15064
    Prev
    Next
    INDEX
    Explanations

    say "fat terminology"

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

    No Comments

    Negative Logits
    WithURL
    -17.13
     URLs
    -16.88
    ürger
    -16.63
     Raphael
    -16.63
    _urls
    -16.38
    蟒
    -16.25
    fern
    -16.13
     Docs
    -16.13
    輩
    -16.13
    urls
    -16.00
    POSITIVE LOGITS
     lean
    18.13
     adip
    17.63
    etro
    15.00
    廪
    14.56
    肪
    14.00
    仓储
    13.50
    Lean
    13.44
    皮
    13.06
    油脂
    13.06
     Oil
    13.00
    Activations Density 0.059%

    No Known Activations