© 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. 37067
    Prev
    Next
    INDEX
    Explanations

    city names followed by City

    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
    躬
    -0.09
    ingen
    -0.08
    豫
    -0.08
    æ¯Ķä¾ĭ
    -0.08
    idot
    -0.08
    èİ«åIJį
    -0.08
    vier
    -0.08
    æīŃæĽ²
    -0.07
    æĪĪ
    -0.07
     Master
    -0.07
    POSITIVE LOGITS
     CITY
    0.11
    åŁİ
    0.11
     City
    0.11
    ä¸Ńå¿ĥåŁİå¸Ĥ
    0.11
    室
    0.10
    éģ¿
    0.10
    -city
    0.10
    åĿ¨
    0.10
     city
    0.10
    å¸Ĥ
    0.10
    Activations Density 0.104%

    No Known Activations