© 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. 6317
    Prev
    Next
    INDEX
    Explanations

    nursing homes, elder care, assisted living

    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»ĵ
    -0.11
    é¢Ķ
    -0.09
    åºĹ主
    -0.09
    å¸ĤæķĻèĤ²
    -0.09
     EÄŁitim
    -0.09
     Ðļи
    -0.09
    ç«¥è£ħ
    -0.09
    åĬŀåħ¬å®¤
    -0.09
    æīĺè¿IJ
    -0.09
    hsi
    -0.09
    POSITIVE LOGITS
    åħ»èĢģ
    0.23
    èĢģ年人
    0.21
    èĢģå¹´
    0.17
    èĢģ人
    0.17
    åħ»èĢģæľįåĬ¡
    0.15
    elder
    0.14
    èĢģ人家
    0.14
     elderly
    0.13
    æĻļå¹´
    0.13
     dementia
    0.13
    Activations Density 0.185%

    No Known Activations