© 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. 20853
    Prev
    Next
    INDEX
    Explanations

    events and states

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    æĢİä¹ĪåĬŀ
    -0.09
    ä¸įæĩĪ
    -0.09
    thon
    -0.08
    æ£Ħ
    -0.08
    å¼ĥ
    -0.08
    ä¹ĸ
    -0.08
     ank
    -0.08
    æĺİæĻº
    -0.08
    åĬłä¸Ĭ
    -0.08
    åѦä¼ļ
    -0.08
    POSITIVE LOGITS
     lasts
    0.11
    æĹ¨åľ¨
    0.11
    åĪĨ为
    0.10
    éĢĤçĶ¨äºİ
    0.10
    æľī两ç§į
    0.09
    ä¸Ģç»ı
    0.09
    缮åīįå·²
    0.09
    åı¯åĪĨ为
    0.09
    åı¯ä»¥æł¹æį®
    0.09
    äº
    0.09
    Activations Density 0.257%

    No Known Activations