© 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. 51183
    Prev
    Next
    INDEX
    Explanations

    liquid, solid, and gaseous matter

    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
    åĨįçĶŁ
    -0.10
    çħ
    -0.10
    çĬģ
    -0.09
    鹿
    -0.09
    足
    -0.09
     Timeline
    -0.09
    骧
    -0.09
     Rubin
    -0.09
    &w
    -0.09
     farms
    -0.09
    POSITIVE LOGITS
    ä»Ĺ
    0.09
     med
    0.09
    æħ£ãĤĮ
    0.08
    åĨ¥
    0.08
    åįĬ天
    0.08
     electronics
    0.08
     electronic
    0.08
    è¿Ļåľº
    0.08
    åĪļ
    0.08
     electrónico
    0.08
    Activations Density 0.112%

    No Known Activations