© 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. 10580
    Prev
    Next
    INDEX
    Explanations

    debut album

    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
    uil
    -0.21
    ä¸Ģ个人
    -0.20
    QRST
    -0.20
    ä¹°ä¸ľè¥¿
    -0.20
    æķĻæİĪ
    -0.19
     LIS
    -0.19
    -rad
    -0.19
    ä¸ĢåĢĭ人
    -0.19
    ilater
    -0.18
    è§Ĩéĩİ
    -0.18
    POSITIVE LOGITS
    å¤ĩ
    0.22
    第ä¸Ģ
    0.22
    æĪIJåĬŁä¸¾åĬŀ
    0.22
    主线
    0.21
    主æīĵ
    0.20
    太平æ´ĭ
    0.20
    strup
    0.20
    ç¢Ł
    0.19
    举åĬŀäºĨ
    0.19
    æĪIJç«ĭ以æĿ¥
    0.19
    Activations Density 0.106%

    No Known Activations