© 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. 10671
    Prev
    Next
    INDEX
    Explanations

    disaster recovery and rebuilding efforts

    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
    Not in Any Lists

    No Comments

    Negative Logits
    é¦Ĩ
    -0.23
    ä¼łæĴŃ
    -0.19
    çľĭä»ĸ
    -0.18
    ä»ĸæĺ¯
    -0.18
     continents
    -0.18
    faction
    -0.18
    æĪIJåŀĭ
    -0.18
    éĶŃ
    -0.18
     sud
    -0.18
    host
    -0.18
    POSITIVE LOGITS
    æĪ¿å±ĭ
    0.24
    izo
    0.23
    æģ¢å¤į
    0.22
    æݾ
    0.21
    æĪ¿
    0.20
    ç¼®
    0.20
    åıĹçģ¾
    0.20
    åĭĺæŁ¥
    0.19
    zilla
    0.19
    Ĭ¶
    0.19
    Activations Density 0.013%

    No Known Activations