© 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. 36595
    Prev
    Next
    INDEX
    Explanations

    male pronouns and possessives

    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
    å¨ĺ家
    -0.15
    ä¸Ī夫
    -0.13
    å«ģç»Ļ
    -0.13
     herself
    -0.13
     должна
    -0.12
     ÙĨÙģسÙĩا
    -0.11
    ese
    -0.10
     ÑģÑĤала
    -0.10
    èĢģåħ¬
    -0.10
    纤维
    -0.10
    POSITIVE LOGITS
    /she
    0.17
    åijĬè¯ī她
    0.14
    çļĦ妻åŃIJ
    0.13
    /her
    0.13
    媳å¦ĩ
    0.12
    ç»Ļ她
    0.12
     himself
    0.11
     await
    0.11
    "She
    0.10
    媳
    0.10
    Activations Density 0.228%

    No Known Activations