© 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. 39236
    Prev
    Next
    INDEX
    Explanations

    toilets and bathroom facilities

    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
    æijĩ
    -0.12
    æIJĸ
    -0.09
    èĪŁ
    -0.09
    丧
    -0.09
    æģĥ
    -0.09
    éŃĶé¾Ļ
    -0.09
    ogne
    -0.09
    èݪ
    -0.09
    nen
    -0.09
    å¯Ħæīĺ
    -0.09
    POSITIVE LOGITS
    åİķæīĢ
    0.14
    ãĥĪãĤ¤ãĥ¬
    0.13
     pee
    0.12
     bathroom
    0.11
     ur
    0.11
    åİķ
    0.11
    å°¿
    0.11
     Bathroom
    0.10
     urine
    0.10
    蹬
    0.09
    Activations Density 0.036%

    No Known Activations