© 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. 20435
    Prev
    Next
    INDEX
    Explanations

    particulate

    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
    æĭĬ
    -0.10
    rial
    -0.10
    åħ®
    -0.09
    ãĥ¬ãĤ¹
    -0.09
    该åİ¿
    -0.09
    å²Ĥ
    -0.09
    åĶ®
    -0.08
    akh
    -0.08
    大éħĴåºĹ
    -0.08
    容
    -0.08
    POSITIVE LOGITS
    colo
    0.09
    临
    0.09
    ople
    0.09
    æ´»å¾Ĺ
    0.08
    _PROP
    0.08
     beyond
    0.08
    uration
    0.08
    éĩijåŃĹ
    0.08
     sparing
    0.08
    饯
    0.08
    Activations Density 0.004%

    No Known Activations