© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12234
    Prev
    Next
    INDEX
    Explanations

    final user, most individuals, food producers, foreign DNA

    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
    çݯå¢ĥ污æŁĵ
    -0.20
    æķ£åıijçĿĢ
    -0.18
    对æĸ¹
    -0.18
    ãģĦãģ¤ãĤĤ
    -0.18
    ä¸ı
    -0.18
    æķĻæĿIJ
    -0.18
    æݨèįIJéĺħ读
    -0.18
    ä¸Ģçĵ¶
    -0.17
    ä¸ĢçĽ´æ²¡æľī
    -0.17
    æŃ»äºĨ
    -0.17
    POSITIVE LOGITS
    çĶ¨æĪ·æıIJä¾Ľ
    0.30
    ä¼ģä¸ļæıIJä¾Ľ
    0.20
    åĺĽ
    0.20
    æľĢ大ç¨ĭ度
    0.20
    们
    0.19
    åıĤä¸İåĪ°
    0.19
    åľ¨åħ¶
    0.19
    â
    0.19
    享åıĹåĪ°
    0.19
     DISCLAIMER
    0.18
    Activations Density 0.166%

    No Known Activations