© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 302
    Prev
    Next
    INDEX
    Explanations

    say neural network

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

    No Comments

    Negative Logits
    ildo
    -20.75
     Arkansas
    -19.50
    インド
    -19.00
    茂名
    -18.88
     Dutch
    -18.88
    佛山
    -18.88
     Southwest
    -18.63
    东莞
    -18.50
    柞
    -18.13
    肇庆
    -17.88
    POSITIVE LOGITS
    神经
    27.88
    训练
    27.38
     neural
    26.00
     Neural
    25.88
     TensorFlow
    25.25
     Tensor
    23.00
    Tensor
    23.00
     training
    22.25
     tensorflow
    21.63
     cnn
    21.63
    Activations Density 0.218%

    No Known Activations