© 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. 3360
    Prev
    Next
    INDEX
    Explanations

    legs, tights, socks, boots

    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
    (mut
    -0.26
    é¼¾
    -0.26
     Stafford
    -0.25
    çĪ¶åŃIJ
    -0.23
    å²ŃåįĹ
    -0.23
    æķĸ
    -0.23
    åŃIJåŃĻ
    -0.23
    éĥ¨èIJ½
    -0.23
     Aws
    -0.22
    赦
    -0.21
    POSITIVE LOGITS
    å¦Ĩ
    0.31
    è£Ļ
    0.28
     transparency
    0.26
     elegant
    0.26
     ladies
    0.26
     powder
    0.26
     elegance
    0.25
    åĮĸå¦Ĩåĵģ
    0.25
     Transparency
    0.25
    /video
    0.25
    Activations Density 0.004%

    No Known Activations