© 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. 7746
    Prev
    Next
    INDEX
    Explanations

    engaged and married

    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
    isen
    -0.09
    æ±ģ
    -0.08
    æĬĺ
    -0.08
    çĥŃéĶĢ
    -0.08
    é¢Ĩè·ij
    -0.08
    éĺħè§Ī
    -0.08
    ализ
    -0.08
    éĶĢæ¯ģ
    -0.07
    è¯Ħè®®
    -0.07
    tit
    -0.07
    POSITIVE LOGITS
    娶
    0.22
    å©ļ姻
    0.20
    ç»ĵå©ļ
    0.20
    å«ģ
    0.19
    å«ģç»Ļ
    0.19
     marriage
    0.19
    å©ļ
    0.18
    å©ļ礼
    0.17
     marriages
    0.15
    æ±Ĥå©ļ
    0.15
    Activations Density 0.074%

    No Known Activations