© 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. 37204
    Prev
    Next
    INDEX
    Explanations

    EU related institutions and regulations

    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
    èIJ½åħ¥
    -0.09
     Jade
    -0.09
    ä¸Ģ件äºĭ
    -0.08
    åĩıåĢ¼
    -0.08
    çİīçŁ³
    -0.08
    æ´»çĿĢ
    -0.08
    isch
    -0.08
     jade
    -0.08
    åħ¨æµģç¨ĭ
    -0.08
    .classes
    -0.08
    POSITIVE LOGITS
    æ¬§çĽŁ
    0.13
    EU
    0.12
    .eu
    0.12
    欧洲
    0.11
     EU
    0.10
    驳
    0.10
    欧åħĥ
    0.10
     harmon
    0.10
    éĢĤçĶ¨
    0.10
     European
    0.09
    Activations Density 0.295%

    No Known Activations