© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 16375
    Prev
    Next
    INDEX
    Explanations

    prominent, company, church, Geneva

    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
    é¢Ĭ
    -0.21
    åī¥
    -0.20
    å½Ŀ
    -0.20
    ç»ıèIJ¥æ¨¡å¼ı
    -0.19
    bang
    -0.19
    绦
    -0.18
    æĶ¿çŃĸæݪæĸ½
    -0.18
    ocha
    -0.18
    Convention
    -0.18
    åij¨åĽ´çļĦ
    -0.18
    POSITIVE LOGITS
     unnamed
    0.29
     undisclosed
    0.23
     unspecified
    0.22
     ap
    0.22
    æŁIJä¸Ģ
    0.21
    轸
    0.20
    æŁIJ
    0.20
    unn
    0.19
    女æĢ§æľĭåıĭ
    0.19
     university
    0.19
    Activations Density 0.257%

    No Known Activations