© 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. 17185
    Prev
    Next
    INDEX
    Explanations

    big followed by significant nouns

    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
    ONS
    -0.21
    åģļæ³ķ
    -0.21
    è¶ĬæĿ¥è¶Ĭå¤ļ
    -0.20
     ÑģамÑĭе
    -0.19
     اÙĦÙħزÙĬد
    -0.18
    æĽ´åħ·
    -0.17
    æĽ´
    -0.17
    çĶļ
    -0.17
    å°ijéĩı
    -0.17
    æĽ´éĢĤåIJĪ
    -0.17
    POSITIVE LOGITS
    oted
    0.26
    ä¸įå°ıçļĦ
    0.22
    -league
    0.21
    åħ³åĪĩ
    0.19
    èħ¥
    0.19
    ä¸įå°ı
    0.19
    èį£å¹¸
    0.18
     emphasis
    0.18
    gie
    0.18
    /big
    0.18
    Activations Density 0.026%

    No Known Activations