© 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. 17149
    Prev
    Next
    INDEX
    Explanations

    and/or other contributors

    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
    çĶļèĩ³
    -0.30
     tháºŃm
    -0.28
    çĶļèĩ³æĺ¯
    -0.28
     even
    -0.28
    å¹²èĦĨ
    -0.25
    以èĩ³äºİ
    -0.25
    even
    -0.23
    çĶļèĩ³è¿ŀ
    -0.23
    åĵªæĢķ
    -0.22
     sogar
    -0.22
    POSITIVE LOGITS
    ãģ³
    0.21
    çĶŁäº§åĴĮ
    0.20
    arLayout
    0.20
    isplay
    0.20
    estroy
    0.20
    èĶ¼
    0.19
    è´¨éĩıåĴĮ
    0.19
    ineTransform
    0.19
    æŶéĹ´åĴĮ
    0.19
    æĸĩåĮĸåĴĮ
    0.19
    Activations Density 0.380%

    No Known Activations