© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 23583
    Prev
    Next
    INDEX
    Explanations

    women and girls

    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
    娶
    -0.13
     himself
    -0.12
    çĪ¶åŃIJ
    -0.11
    äºĨä»ĸçļĦ
    -0.11
    çļĦ妻åŃIJ
    -0.11
    夫å¦ĩ
    -0.10
    夫妻
    -0.09
    æ±Ĥå©ļ
    -0.09
    ä¸Ģ家人
    -0.09
     sexually
    -0.09
    POSITIVE LOGITS
    她们
    0.19
    å§IJ妹
    0.14
    éĹºèľľ
    0.13
    妯
    0.11
    女æĢ§
    0.11
    å¦ĩç§ij
    0.10
     ladies
    0.10
    女人
    0.10
    çijľä¼½
    0.10
     daughters
    0.10
    Activations Density 0.185%

    No Known Activations