© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 421
    Prev
    Next
    INDEX
    Explanations

    say oil

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

    No Comments

    Negative Logits
     Johannesburg
    -23.63
     Rwanda
    -20.88
     Zimbabwe
    -20.50
     BTS
    -20.13
    锑
    -19.63
     iPhones
    -18.50
    手机
    -18.00
    _mobile
    -18.00
    ANGO
    -17.63
     iPhone
    -17.50
    POSITIVE LOGITS
     oil
    26.75
     Oil
    26.38
    海洋
    26.00
    油
    25.50
     Omega
    25.38
     omega
    25.25
    Oil
    24.25
    油脂
    23.75
     marine
    23.63
     oils
    23.63
    Activations Density 0.079%

    No Known Activations