© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 3401
    Prev
    Next
    INDEX
    Explanations

    user orders customer workflow assigned invoice

    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
    Negative Logits
    engu
    -0.28
    _argv
    -0.28
     brilliantly
    -0.28
    .Arg
    -0.27
    .Sockets
    -0.27
     famously
    -0.26
    欣èµı
    -0.26
    .www
    -0.26
    LIBINT
    -0.26
    _heap
    -0.26
    POSITIVE LOGITS
    æĺİç»Ĩ
    0.37
    åŃĹ段
    0.37
    åħ³èģĶ
    0.35
     invoice
    0.34
     workflow
    0.34
    å½ķåħ¥
    0.34
     assigned
    0.34
    ä¸ļåĬ¡
    0.34
     customer
    0.33
     granularity
    0.33
    Activations Density 0.896%

    No Known Activations