© 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. 17110
    Prev
    Next
    INDEX
    Explanations

    Easy, but, book, it, what

    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
    åĬ£
    -0.19
    缫
    -0.18
    ÑģÑĤÑĭ
    -0.18
    好åĩłä¸ª
    -0.18
    ï¼Īç¬ij
    -0.18
    éĤĪ
    -0.18
    åĴĿ
    -0.17
    沮丧
    -0.17
    æĪIJè¯Ń
    -0.17
    uttle
    -0.17
    POSITIVE LOGITS
     Redistributions
    0.23
    æĺ¯åĽłä¸º
    0.22
    æĺ¯ä¸ºäºĨ
    0.22
    and
    0.21
    org
    0.21
     поÑģколÑĮ
    0.21
    éĤ£æł·
    0.19
     заÑĢегиÑģÑĤ
    0.18
    并éĢļè¿ĩ
    0.18
     ÐIJлекÑģан
    0.18
    Activations Density 0.017%

    No Known Activations