© 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. 11253
    Prev
    Next
    INDEX
    Explanations

    Jay-Z, Z, Bezos, Wiggins

    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
    æ¦
    -0.20
    为ä»Ģä¹Īä¼ļ
    -0.19
    åŁºæľ¬ä¸Ĭéĥ½
    -0.19
    åºĶæĶ¶
    -0.19
    溯æºIJ
    -0.19
    鸬
    -0.18
    èĽ¾
    -0.18
    室
    -0.18
    ete
    -0.18
    å¿Ĺ强
    -0.17
    POSITIVE LOGITS
    ipur
    0.21
    èµĮ
    0.21
    çݰ身
    0.21
    æĪIJåĬŁ
    0.19
    稳
    0.19
     Blueprint
    0.19
    åħ»
    0.18
     Palin
    0.18
    å®ļäºĨ
    0.18
    æĪIJåĬŁçļĦ
    0.18
    Activations Density 0.001%

    No Known Activations