© 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. 17231
    Prev
    Next
    INDEX
    Explanations

    legal cases

    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
    æĿľç»Ŀ
    -0.20
    ä¹ŁæĪIJ为
    -0.20
    æĪijå¸Ĥ
    -0.19
    á¿ij
    -0.18
    æĪij们çļĦ
    -0.18
     closest
    -0.17
    æĺİå¹´
    -0.17
    åīį身
    -0.17
     Flip
    -0.17
    å»ĵ
    -0.17
    POSITIVE LOGITS
    ç»ĻåĪ«äºº
    0.24
    ç»Ļèĩªå·±
    0.23
    ç»Ļ人
    0.23
    æŁIJç§į
    0.22
    çī©ä½ĵ
    0.21
    为èĩªå·±
    0.21
    åľºåIJĪ
    0.20
    æŁIJ个
    0.20
    ож
    0.20
    té
    0.20
    Activations Density 0.054%

    No Known Activations