© 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. 54481
    Prev
    Next
    INDEX
    Explanations

    toilet, bathroom, poop, unisex

    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
    æIJ¬å®¶
    -0.09
    è¿ĩæĪ·
    -0.09
    mes
    -0.08
    æħİéĩį
    -0.08
    èĢģåĮĸ
    -0.08
    ç¼ĸåĪ¶
    -0.08
    ä¹Ŀ大
    -0.08
    åįıä¼ļä¼ļåijĺ
    -0.08
    åģ¿
    -0.08
    å°±ä¸įèĥ½
    -0.08
    POSITIVE LOGITS
    åİķæīĢ
    0.16
    åİķ
    0.15
    马桶
    0.13
    ãĥĪãĤ¤ãĥ¬
    0.13
     Toilet
    0.12
     restroom
    0.12
     bathroom
    0.11
     Bathroom
    0.11
    æ´Ĺæīĭ
    0.11
    athroom
    0.11
    Activations Density 0.280%

    No Known Activations