© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 61082
    Prev
    Next
    INDEX
    Explanations

    European Union, EUR, European countries

    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
    çĪ±åĽ½ä¸»ä¹ī
    -0.09
    ëĿ½
    -0.08
    大äºĭ
    -0.08
    æŃ¤é¡¹
    -0.08
     sodom
    -0.08
    BOSE
    -0.08
     Breitbart
    -0.08
    redient
    -0.08
    åIJĦåİ¿
    -0.08
    éĥ¨ä¸»ä»»
    -0.08
    POSITIVE LOGITS
    æ¬§çĽŁ
    0.15
    欧洲
    0.13
    ä¸ĩ欧åħĥ
    0.13
    欧åħĥ
    0.12
     EUR
    0.12
    EUR
    0.11
    åľ¨åħ¨çIJĥ
    0.11
    EU
    0.11
     âĤ¬
    0.11
     European
    0.11
    Activations Density 1.327%

    No Known Activations