© 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. 17275
    Prev
    Next
    INDEX
    Explanations

    for introducing purpose or action

    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
    nut
    -0.20
    æľīæīĢ
    -0.19
    æĪİ
    -0.19
    æľºä¼ļ
    -0.19
     som
    -0.18
    æľīæĽ´å¥½çļĦ
    -0.18
    æľīæŶåĢĻ
    -0.18
    или
    -0.18
     sometimes
    -0.18
     having
    -0.18
    POSITIVE LOGITS
    éĺ²æŃ¢
    0.27
    åĪ¶æŃ¢
    0.21
    çĶĦ
    0.21
    æĶ¶éĽĨ
    0.21
    解åĨ³
    0.21
    ä¿ĥè¿Ľ
    0.21
    åĮºåĪĨ
    0.20
    éĺ»æŃ¢
    0.20
    æ£Ģæµĭ
    0.20
     Ñĥдал
    0.20
    Activations Density 0.299%

    No Known Activations