© 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. 10605
    Prev
    Next
    INDEX
    Explanations

    "After"

    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
     bas
    -0.23
    hen
    -0.23
    æµģ
    -0.21
    éĢļ
    -0.19
    æĺİ
    -0.19
    象
    -0.19
    å®ļ
    -0.19
    s
    -0.18
    i
    -0.18
    olt
    -0.18
    POSITIVE LOGITS
    æĮ¡ä½ı
    0.21
    åĺ´éĩĮ
    0.21
    åľ¨çݩ家ä¸Ń
    0.19
     Açık
    0.19
    é«ĺ涨
    0.19
    è¿ĻäºĽéĥ½æĺ¯
    0.19
    说å®Į
    0.19
    èĬ¡
    0.19
     noqa
    0.19
    åĢĴéľī
    0.19
    Activations Density 0.099%

    No Known Activations