© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 961
    Prev
    Next
    INDEX
    Explanations

    say Kafka

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

    No Comments

    Negative Logits
    莳
    -19.88
    马来西亚
    -18.25
     Newport
    -18.13
    筼
    -17.75
     Malaysian
    -17.75
    杵
    -17.50
    Berry
    -17.38
    钢板
    -17.13
    港澳
    -17.00
    渤海
    -17.00
    POSITIVE LOGITS
     Kafka
    44.50
     kafka
    41.00
    .kafka
    35.50
    afka
    27.50
     consumer
    26.13
     Zoo
    25.88
     consumers
    25.63
     zoo
    25.00
    乳业
    24.38
    消费者
    24.00
    Activations Density 0.021%

    No Known Activations