© 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. 15653
    Prev
    Next
    INDEX
    Explanations

    say natural materials

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

    No Comments

    Negative Logits
    顾问
    -24.38
     Advisor
    -23.00
    _CON
    -21.00
     advisor
    -20.88
     adviser
    -20.50
    advert
    -19.75
     Advisors
    -19.50
     advisory
    -19.50
    con
    -19.38
    conc
    -19.13
    POSITIVE LOGITS
    纱
    22.13
     grain
    21.88
     Grain
    21.63
    蜜
    20.13
    纤维
    19.25
     McCartney
    19.00
     grains
    18.75
     Gem
    18.50
    fiber
    18.38
    影片
    18.25
    Activations Density 2.241%

    No Known Activations