© 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. 36974
    Prev
    Next
    INDEX
    Explanations

    protagonist or main character

    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
     ÙĪØ£ÙĨ
    -0.10
    ä¸¥æł¼çļĦ
    -0.09
    URY
    -0.09
    antan
    -0.09
    iry
    -0.08
    orde
    -0.08
    å«Ĥ
    -0.08
    大æĪ·
    -0.08
    åİŁå§ĭ
    -0.08
    ening
    -0.08
    POSITIVE LOGITS
    人çī©
    0.12
    ASTER
    0.09
    åĽ¡
    0.09
    inski
    0.09
    /main
    0.09
    ·æĸ°
    0.09
    kits
    0.08
    é¢Ŀ
    0.08
    ä¹ĭä¸Ģ
    0.08
    çļĦçĪ¶äº²
    0.08
    Activations Density 0.035%

    No Known Activations