© 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. 17104
    Prev
    Next
    INDEX
    Explanations

    medical director, advance directives, OAuth

    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
     dumb
    -0.19
    æ¸IJ
    -0.18
     foss
    -0.18
    -signed
    -0.17
    éļIJ
    -0.17
    ÐĿÐĺ
    -0.17
    认åIJĮ
    -0.17
    è¿Ľè¡Įåħ¨éĿ¢
    -0.17
    controllers
    -0.17
     cryst
    -0.17
    POSITIVE LOGITS
    åĪ¶åº¦æĶ¹éĿ©
    0.24
    çĶ¨æĪ·çļĦ
    0.24
    æ¶Īè´¹èĢħçļĦ
    0.23
    大æī¹
    0.22
    è®©æĽ´å¤ļ
    0.22
    为广大
    0.21
    客æĪ·çļĦ
    0.20
    æĹłæķ°
    0.20
    åѦçĶŁä»¬
    0.20
    ä¸Ģæī¹
    0.20
    Activations Density 0.312%

    No Known Activations