© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 10435
    Prev
    Next
    INDEX
    Explanations

    theatre, show, London, Africa

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    åħ¨éķĩ
    -0.24
    åħ¨åİ¿
    -0.22
    ç»ĻåĪ«äºº
    -0.21
    å¯Ŀ室
    -0.21
    âĻ¬
    -0.20
    åIJĦåİ¿
    -0.20
    ç»Ļä½łä»¬
    -0.20
    æĬĬè¿ĻäºĽ
    -0.19
    _DRV
    -0.19
    Reusable
    -0.19
    POSITIVE LOGITS
    çģı
    0.23
    ä¸ľäº¬
    0.22
    帷
    0.21
    é«ĺä»·
    0.20
    æĹħ客
    0.20
    çĭİ
    0.20
     Millions
    0.20
    京åŁİ
    0.20
    aron
    0.20
    London
    0.20
    Activations Density 0.027%

    No Known Activations