© 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. 17114
    Prev
    Next
    INDEX
    Explanations

    describing positive qualities

    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
     ho
    -0.20
     Bott
    -0.18
     or
    -0.18
    åŁºæľ¬ä¸Ĭéĥ½
    -0.18
     glorious
    -0.18
     inability
    -0.18
     absence
    -0.17
    æĽ´åĥıæĺ¯
    -0.17
    æĪĸåħ¶ä»ĸ
    -0.17
    æĪijè§īå¾Ĺ
    -0.17
    POSITIVE LOGITS
    åı¯éĿł
    0.28
    å®ŀæĥł
    0.27
    é«ĺæķĪ
    0.26
    åħ¬æŃ£
    0.25
    ç¾İè§Ĥ
    0.25
    åĩĨç¡®
    0.24
     bá»ģn
    0.23
    å®ŀçĶ¨
    0.23
    精确
    0.23
    é«ĺæķĪçļĦ
    0.23
    Activations Density 0.084%

    No Known Activations