© 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. 17154
    Prev
    Next
    INDEX
    Explanations

    units with fractions and measurements

    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
    åIJĥ饱
    -0.20
    è¿Ļå¼ł
    -0.18
    enas
    -0.18
    numer
    -0.18
    athi
    -0.18
     sc
    -0.18
    roy
    -0.17
    èħ½
    -0.17
     bidi
    -0.17
    ä¸īç§į
    -0.17
    POSITIVE LOGITS
    履约
    0.21
     iota
    0.19
    [".
    0.18
    社ä¼ļåĮĸ
    0.18
    åĩºçĶŁ
    0.17
    åĢ¬
    0.17
    æĽ
    0.17
    æ°ijæĶ¿
    0.17
    åĺ´éĩĮ
    0.17
    对éĿ¢
    0.17
    Activations Density 0.027%

    No Known Activations