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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8168
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    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
    åĭĺæŁ¥
    -0.09
    æī¾äºĨ
    -0.09
     sek
    -0.09
    åİŁå§ĭ
    -0.09
    å¤ļä½į
    -0.09
    åİ»æī¾
    -0.08
    æĽ´éĢĤåIJĪ
    -0.08
    èĦ¯
    -0.08
    å¯Ĵ
    -0.08
     лиÑĩно
    -0.08
    POSITIVE LOGITS
     enforce
    0.12
    强åĪ¶
    0.12
    æĿĥå¨ģ
    0.11
    转åĮĸ为
    0.11
    æī§è¡ĮåĬĽ
    0.11
    åıijæĮ¥ä½ľçĶ¨
    0.11
    缴æݥ影åĵį
    0.11
     обÑıзаÑĤелÑĮ
    0.11
    ä»ħä¾ĽåıĤèĢĥ
    0.11
     Enforcement
    0.11
    Activations Density 0.092%

    No Known Activations