© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14299
    Prev
    Next
    INDEX
    Explanations

    say "pollution"

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

    No Comments

    Negative Logits
    .strategy
    -18.88
     kop
    -17.25
     architectures
    -17.25
    策略
    -17.13
    (strategy
    -16.50
     Strategy
    -16.50
    收藏
    -16.50
     forwards
    -16.38
    _strategy
    -16.38
    iben
    -16.25
    POSITIVE LOGITS
     spill
    20.13
     leak
    19.00
    污染
    18.88
     pollution
    18.63
     contaminated
    18.50
    leases
    18.50
    污水
    18.50
     contamination
    17.63
    处理
    17.50
    排污
    17.50
    Activations Density 0.545%

    No Known Activations