© 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. 51701
    Prev
    Next
    INDEX
    Explanations

    antibiotics

    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
     Bray
    -0.10
     snack
    -0.08
    ãĤ¨ãĥ³
    -0.08
    kol
    -0.08
    æħķ
    -0.08
    TestMethod
    -0.08
    esting
    -0.08
    CLU
    -0.08
    esti
    -0.08
    èĨĬ
    -0.08
    POSITIVE LOGITS
     antibiotics
    0.16
    æĬĹçĶŁç´ł
    0.15
    æĿĢèıĮ
    0.15
    æĬĹèıĮ
    0.11
     antibiotic
    0.11
    çĿ«
    0.09
    antas
    0.09
    æĹłæķĪ
    0.09
     antibiot
    0.09
    çĶŁç´ł
    0.09
    Activations Density 0.187%

    No Known Activations