© 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. 17180
    Prev
    Next
    INDEX
    Explanations

    wedding details or planning

    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
    æŀī
    -0.24
    æ¯ĽåŃĶ
    -0.21
    èĩ³å°ij
    -0.20
    .REG
    -0.20
    .GUI
    -0.19
     digest
    -0.19
    rouch
    -0.19
    çĶļèĩ³æĺ¯
    -0.19
     Geile
    -0.18
    ä¸įèĩ³äºİ
    -0.18
    POSITIVE LOGITS
    å¸Ĥåİ¿
    0.21
    å¾ħãģ¡
    0.20
    åŃ³
    0.20
     Dell
    0.19
    å½ĵåľ°æĶ¿åºľ
    0.19
    eldo
    0.19
     facult
    0.18
    ä¼ģä¸ļæıIJä¾Ľ
    0.18
    æĺŁåº§
    0.18
    èĥŀ
    0.18
    Activations Density 0.002%

    No Known Activations