© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 16143
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    æŁŀ
    -0.20
     поÑģÑĤоÑı
    -0.20
    æķ¬
    -0.19
    åĭ¤å¥ĭ
    -0.19
     Advent
    -0.19
    æ½ĩ
    -0.18
    æ´ĭæ´ĭ
    -0.18
    è·Łä»ĸ
    -0.18
    ä¸įåIJĪ
    -0.18
    æİ°
    -0.18
    POSITIVE LOGITS
    ä¸ªå·¥ä½ľæĹ¥
    0.20
    æľīæķĪæľŁ
    0.18
    ROTO
    0.18
    alis
    0.17
    zza
    0.17
    ä¸īæľŁ
    0.17
    æŃ£åľ¨
    0.17
    å¼Ħå¾Ĺ
    0.17
     rem
    0.17
    ron
    0.17
    Activations Density 0.000%

    No Known Activations