© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10033
    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
    æºľ
    -0.10
    åĪģ
    -0.10
    æ»Ķ
    -0.09
    åī½
    -0.09
    æľ½
    -0.09
    åİĨ代
    -0.09
    åŀĥåľ¾
    -0.09
    å°ıä¼Ļä¼´
    -0.09
    Smarty
    -0.09
    ä½ĵè´¨
    -0.08
    POSITIVE LOGITS
    妻
    0.22
    妻åŃIJ
    0.21
    家åºŃ
    0.18
    çļĦ妻åŃIJ
    0.17
     wife
    0.17
    娶
    0.17
    èĢģå©Ĩ
    0.17
    wife
    0.16
    married
    0.15
     married
    0.15
    Activations Density 0.102%

    No Known Activations