© 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. 11507
    Prev
    Next
    INDEX
    Explanations

    nigerian health workers

    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
    nce
    -0.07
    apos
    -0.07
    å¦Ĥæŀľä½łæĥ³
    -0.07
    è¿ĺç®Ĺ
    -0.07
    æ¶Ĥ
    -0.07
     twin
    -0.07
    à¹ģà¸Ľà¸¥
    -0.07
    zens
    -0.07
    	trace
    -0.07
    æij§æ¯ģ
    -0.07
    POSITIVE LOGITS
    éĥ¢
    0.12
    羣è¯ļ
    0.11
    æĶ¾æīĭ
    0.10
    让ä»ĸ们
    0.10
    èħ¼
    0.10
    è´¿
    0.10
    å¾Ģå¾Ģ
    0.10
    对ä»ĸ们
    0.10
    è§Ĥæij©
    0.10
    顺åĪ©å®ĮæĪIJ
    0.10
    Activations Density 0.142%

    No Known Activations