© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21786
    Prev
    Next
    INDEX
    Explanations

    nurse, nurses, nursing

    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
    èģĶè°Ĭ
    -0.10
    交åıī
    -0.09
     Gould
    -0.09
    修为
    -0.09
    rites
    -0.08
    istory
    -0.08
     burdens
    -0.08
    ä¼ijæģ¯
    -0.08
    åŃ£
    -0.08
    æ±ĩèģļ
    -0.08
    POSITIVE LOGITS
    æĬ¤å£«
    0.12
    æĬ¤çIJĨ
    0.12
     Nurses
    0.12
     nurses
    0.12
    ÑĤек
    0.11
     nurse
    0.11
     Nurse
    0.11
     nursing
    0.10
     Nursing
    0.09
     Nurs
    0.09
    Activations Density 0.283%

    No Known Activations