© 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. 15697
    Prev
    Next
    INDEX
    Explanations

    say waste

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

    No Comments

    Negative Logits
    护照
    -21.25
     passport
    -18.13
     infrared
    -17.50
    idis
    -17.00
     Passport
    -16.88
    izard
    -16.88
    虹
    -16.63
    明珠
    -16.25
    passport
    -16.25
    OND
    -16.25
    POSITIVE LOGITS
    垃圾
    24.00
    废弃物
    23.25
     waste
    22.63
    废物
    21.88
     wastes
    21.13
    废
    20.75
    廢
    20.38
     Waste
    20.25
     debris
    19.88
    -de
    19.00
    Activations Density 0.172%

    No Known Activations