© 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. 8693
    Prev
    Next
    INDEX
    Explanations

    Kentucky and surrounding areas

    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
    è¿Ľä¿®
    -0.10
    èĹ»
    -0.09
     Oaks
    -0.09
    èµī
    -0.09
    (rc
    -0.09
    çħ§æł·
    -0.09
    éĢļæĬ¥
    -0.09
    åįļæĸĩ
    -0.09
    ALAR
    -0.09
    é¹Ń
    -0.09
    POSITIVE LOGITS
     Appalach
    0.12
     Kentucky
    0.11
    KY
    0.10
     coal
    0.10
     Indiana
    0.10
    Indiana
    0.10
     Appalachian
    0.10
    çħ¤çŁ¿
    0.10
    åħľ
    0.09
    å´®
    0.09
    Activations Density 0.278%

    No Known Activations