© 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. 3296
    Prev
    Next
    INDEX
    Explanations

    Mario Badescu or other brand names

    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
    _arguments
    -0.24
    iry
    -0.22
    æijĦ
    -0.22
    WindowState
    -0.22
    å¾Ĺ罪
    -0.22
    ESCO
    -0.21
    .setProperty
    -0.21
    irts
    -0.21
    ç½¢
    -0.21
    ä¹ŀ
    -0.21
    POSITIVE LOGITS
    æĶ¿çŃĸæݪæĸ½
    0.22
    æŀĦéĢł
    0.22
    urn
    0.22
    äº¤æĽ¿
    0.22
     paraph
    0.21
    URN
    0.21
    struction
    0.21
     malformed
    0.21
     list
    0.21
     Compilation
    0.20
    Activations Density 0.042%

    No Known Activations