© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1144
    Prev
    Next
    INDEX
    Explanations

    Amazon.com

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Philly
    -0.32
    Philadelphia
    -0.29
    å®Ŀ鸡
    -0.29
     Pittsburgh
    -0.28
    åħ°å·ŀ
    -0.28
     Punjab
    -0.28
     Bulgarian
    -0.27
     Camb
    -0.27
     Slovak
    -0.26
     Philadelphia
    -0.25
    POSITIVE LOGITS
     Amazon
    0.82
    Amazon
    0.71
    äºļ马éĢĬ
    0.70
     amazon
    0.69
    .amazon
    0.68
     AWS
    0.64
     Kindle
    0.62
    amazon
    0.59
    .amazonaws
    0.56
    AWS
    0.56
    Activations Density 0.343%

    No Known Activations