© 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. 17221
    Prev
    Next
    INDEX
    Explanations

    numeric prefixes followed by English words

    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
    æ´
    -0.19
    umont
    -0.18
     tipping
    -0.18
    æĪ®
    -0.18
    uele
    -0.18
    ç¦ıåĪ©
    -0.18
    åĪĿ次
    -0.18
     Leone
    -0.17
    amon
    -0.17
     tipped
    -0.17
    POSITIVE LOGITS
    æľįåĬ¡æľºæŀĦ
    0.20
    å²Ľä¸Ĭ
    0.19
    åīįåı°
    0.18
    ãģĸ
    0.17
    èĮĨ
    0.17
    ä¸įäºĨ
    0.17
    çľĭä¸įæĩĤ
    0.17
    bib
    0.17
    æ£ļ
    0.17
     Emirates
    0.17
    Activations Density 0.003%

    No Known Activations