© 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. 10335
    Prev
    Next
    INDEX
    Explanations

    numbers in ranges or lists

    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
    thèque
    -0.23
    澪
    -0.20
    ãĥĽãĥĨ
    -0.20
    åĬłä»¥
    -0.20
    ç»ıå¼Ģ
    -0.19
    индивид
    -0.19
    æŃ¤åŁºç¡Ģä¸Ĭ
    -0.19
    åıijå±ķéĺ¶æ®µ
    -0.19
    äºĮåįģåĽĽ
    -0.19
    æIJŀ好
    -0.19
    POSITIVE LOGITS
    éĿŀ常å¤ļ
    0.18
     ?:
    0.18
     upwards
    0.18
    éĥ½è®¤ä¸º
    0.17
    èĥ¥
    0.17
     classname
    0.17
    ä¸Ģç±»
    0.17
    -č↵
    0.17
     Parm
    0.17
     evapor
    0.17
    Activations Density 0.181%

    No Known Activations