© 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. 7980
    Prev
    Next
    INDEX
    Explanations

    counties and cities

    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
    åħ¨ä¸ĸçķĮ
    -0.09
    åħ¨åĽ½
    -0.09
    åħ¨çIJĥ
    -0.08
    ä¸ŃåĽ½åĽ½éĻħ
    -0.08
    éĽĨåĽ¢èĤ¡ä»½
    -0.08
    é¢Ĩ
    -0.08
     Philippines
    -0.08
    åįİåįĹ
    -0.08
    åįĹæŀģ
    -0.08
     mát
    -0.08
    POSITIVE LOGITS
    åİ¿
    0.14
    åİ¿åŁİ
    0.12
    该åİ¿
    0.12
     county
    0.12
    åݿ级
    0.11
    åİ¿æĶ¿åºľ
    0.11
    乡éķĩ
    0.11
    åIJĦåİ¿
    0.11
     counties
    0.11
    縣
    0.11
    Activations Density 0.328%

    No Known Activations