© 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. 17268
    Prev
    Next
    INDEX
    Explanations

    percent of vote

    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
    榷
    -0.21
     fant
    -0.20
    zar
    -0.20
    æľīæĦıä¹ī
    -0.20
    åįģå¤ļå¹´
    -0.20
    æľī趣
    -0.19
    æĢĽ
    -0.19
    gend
    -0.18
    eled
    -0.18
    Endian
    -0.18
    POSITIVE LOGITS
    å§Ķåijĺ
    0.24
    è°ĥçłĶ
    0.24
    éĹ®åį·
    0.22
    票
    0.20
    çľ¼åħī
    0.20
    á»ıi
    0.20
     preseason
    0.20
    æľĢå¤ļçļĦ
    0.19
    ä¼Ĺ
    0.19
    ç£ķ
    0.19
    Activations Density 0.017%

    No Known Activations