© 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. 38285
    Prev
    Next
    INDEX
    Explanations

    antibiotic use and resistance

    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
    fully
    -0.10
    æ¦ĩ
    -0.10
    IMENT
    -0.10
    åī¡
    -0.09
    OLVE
    -0.09
    ingles
    -0.09
    æīĭä¸ŃçļĦ
    -0.09
    OfString
    -0.09
    ä¸įéĶĻçļĦ
    -0.09
    usz
    -0.09
    POSITIVE LOGITS
    ä¸įéĶĪ
    0.09
    aken
    0.09
    ë¥ĺ
    0.08
    Ãłn
    0.08
     ÙĪاÙĦÙģ
    0.08
    岸
    0.08
    ores
    0.08
    俪
    0.08
    -free
    0.08
    çķĮçļĦ
    0.08
    Activations Density 0.051%

    No Known Activations