© 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. 10461
    Prev
    Next
    INDEX
    Explanations

    fields of knowledge and policy

    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
    干活
    -0.23
    è¡Į使
    -0.21
    ãĤĪãģĨãģª
    -0.20
    è¿Ļæł·åģļ
    -0.19
    ä¸ªå·¥ä½ľ
    -0.19
    ä»Ģä¹ĪåİŁåĽł
    -0.19
    Semantic
    -0.19
    åı¯çĶ¨äºİ
    -0.18
    çĶŁäº§çĶŁæ´»
    -0.18
    åıįä¹ĭ
    -0.18
    POSITIVE LOGITS
    ä¸Ńæľī
    0.26
    ä¸ŃçļĦ
    0.25
    åı²ä¸Ĭ
    0.24
    çļĦé«ĺ度
    0.23
    oller
    0.21
    ä¸ŃæľĢ
    0.20
    大åݦ
    0.20
    çļĦæķ´ä½ĵ
    0.20
    uisse
    0.20
    æĸ°æł¼å±Ģ
    0.20
    Activations Density 0.262%

    No Known Activations