© 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. 10594
    Prev
    Next
    INDEX
    Explanations

    comes after comma

    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
    天天
    -0.18
    åĭ¤
    -0.18
    ynch
    -0.18
     ayr
    -0.17
     aba
    -0.17
     Milo
    -0.17
    awl
    -0.17
    æľį
    -0.17
    ãģ¯ãģĺãĤģ
    -0.17
    isan
    -0.17
    POSITIVE LOGITS
    è¿ĺæľīä¸Ģ个
    0.27
    åħ¶ä»ĸçļĦ
    0.23
    è¿ĺæľīä¸ĢäºĽ
    0.22
    人群ä¸Ń
    0.22
    æľīæŶ
    0.22
    ä»Ģä¹Īåij¢
    0.21
    åĨįåĬłä¸Ĭ
    0.21
    åħ¶å®ĥ
    0.21
    æĺ¯ä»Ģä¹Īåij¢
    0.21
    åħ¶ä»ĸåĽ½å®¶
    0.20
    Activations Density 0.149%

    No Known Activations