© 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. 10637
    Prev
    Next
    INDEX
    Explanations

    recently gained

    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
    Not in Any Lists

    No Comments

    Negative Logits
    äºĽä»Ģä¹Ī
    -0.23
    _ES
    -0.20
    æĮģ
    -0.19
    éĩįçĶŁ
    -0.19
    ä¸Ģå®ļçļĦ
    -0.19
    amodel
    -0.18
    ç§ijæĬĢåĽŃ
    -0.18
    åĸĿäºĨ
    -0.18
    åĨįçĶŁ
    -0.18
    å³°ä¼ļ
    -0.18
    POSITIVE LOGITS
    æīįåıijçİ°
    0.31
    æīį
    0.27
    æīįçŁ¥éģĵ
    0.27
    å¼Ģå§ĭ
    0.26
    æŃ£å¼ı
    0.24
    å§ĭ
    0.23
    羣æŃ£
    0.23
    æĪijæīį
    0.22
    æĥ³èµ·æĿ¥
    0.22
    羣æŃ£çļĦ
    0.22
    Activations Density 0.046%

    No Known Activations