© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51895
    Prev
    Next
    INDEX
    Explanations

    emergency medical services

    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
    lesi
    -0.10
    æݧ
    -0.09
    enden
    -0.09
    污æŁĵçī©
    -0.09
    ä¸įæ¸ħæ¥ļ
    -0.09
    å¹ķåIJİ
    -0.09
    flake
    -0.09
    åı¤æĢª
    -0.09
    çĸµ
    -0.09
    ä¸įå®ļ
    -0.09
    POSITIVE LOGITS
    éĺŁä¼į
    0.09
     crews
    0.08
    jug
    0.08
     responder
    0.08
    éĺŁä¼į建设
    0.08
    Responder
    0.08
    (Response
    0.08
    Deck
    0.07
    éĢģ
    0.07
     vez
    0.07
    Activations Density 0.019%

    No Known Activations