© 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
    2. Qwen3-14B
    3. 20-RESID-BATCHTOPK-65K__L0-80
    4. 10336
    Prev
    Next
    INDEX
    Explanations

    testing and subsequent actions

    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
    使çĶ¨ç¶²è·¯
    -0.20
    åĪ©ç͍æĤ¨çļĦ
    -0.20
    鸳
    -0.18
    Marshal
    -0.18
    è¾Ĩ车
    -0.18
    ç¯ĩ竳
    -0.18
    çıŃåŃIJæĪIJåijĺ
    -0.18
    æľºä½ĵ
    -0.18
    該使ç͍èĢħ
    -0.18
    cimal
    -0.17
    POSITIVE LOGITS
    ç͍äºİ
    0.20
    developers
    0.19
     stool
    0.19
    å¸Ĥåľºä¸Ĭ
    0.19
     stad
    0.18
    çļĦ帮åĬ©ä¸ĭ
    0.18
     Watt
    0.18
    åı¯ä»¥
    0.18
    èĥ½
    0.18
    çļĦæĪIJæľ¬
    0.18
    Activations Density 0.059%

    No Known Activations