© 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. 17210
    Prev
    Next
    INDEX
    Explanations

    terms of criteria or measurement

    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
    åįı
    -0.19
    åįĶ
    -0.18
    æĻĭæ±Ł
    -0.18
     Clar
    -0.18
    ç§ijæĬĢ大åѦ
    -0.17
    ATIC
    -0.17
    ears
    -0.17
    çļĦæīĢæľī
    -0.17
     Uk
    -0.17
    çĽijå¯Ł
    -0.17
    POSITIVE LOGITS
    è¡¡éĩı
    0.44
     criteria
    0.35
    è¯Ħä»·
    0.32
    èĢĥéĩı
    0.31
    è¯ĦåĪ¤
    0.28
     Criteria
    0.28
    èĥ½åIJ¦
    0.27
     criter
    0.27
    criteria
    0.27
     criterion
    0.26
    Activations Density 0.065%

    No Known Activations