© 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. 10474
    Prev
    Next
    INDEX
    Explanations

    Babymetal Gimme Chocolate

    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
    å¾Ľ
    -0.25
    ÑĩÑĢежден
    -0.24
    è½·
    -0.23
    éľĢè¦ģ
    -0.23
     rel
    -0.23
    à¸Ħà¸ĵะà¸ģรรม
    -0.22
    æĿ¥èĩª
    -0.22
    ð«Ł
    -0.22
     пÑĢиÑıÑĤн
    -0.22
    å¸ĮæľĽ
    -0.21
    POSITIVE LOGITS
    à¹Ĩ
    0.27
    åºĶçĶ¨æŁ¥çľĭ
    0.25
    èµĿ
    0.24
    çı©
    0.22
    åķ¾
    0.22
     à¹Ĩ
    0.22
    ç¼Ĺ
    0.21
    æ½ĭ
    0.21
    çĹĺçĹĺ
    0.21
    æ¤ģ
    0.21
    Activations Density 0.112%

    No Known Activations