© 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. 10396
    Prev
    Next
    INDEX
    Explanations

    mix of

    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
    ä¸Ģ次
    -0.20
    éĻ¤æѤ
    -0.19
    ä¸Ģ声
    -0.19
    æĸ¹åľĨ
    -0.19
    è¿Ļçīĩ
    -0.18
    åijĺ
    -0.18
    è¿Ļ款
    -0.18
    ä¸Ģ件äºĭæĥħ
    -0.18
    ãģ»ãģĨ
    -0.18
    嶷
    -0.17
    POSITIVE LOGITS
     mix
    0.23
    å²ģæŶ
    0.21
    大å°ı
    0.21
    ç»ıéªĮåĴĮ
    0.21
    ä½ĵåĬĽ
    0.20
     mostly
    0.20
     mixed
    0.19
    äºĽ
    0.19
    ï¸
    0.19
     sexes
    0.19
    Activations Density 0.041%

    No Known Activations