© 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. 20872
    Prev
    Next
    INDEX
    Explanations

    Tamil Nadu, people, king

    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
    仡
    -0.10
    çĿ
    -0.09
    åħ¨éĿ¢å»ºæĪIJ
    -0.09
    è¿Ļ两ç§į
    -0.09
    éĩįè¦ģæĦıä¹ī
    -0.08
    illin
    -0.08
     Incorporated
    -0.08
    ä¹ĹãĤĬ
    -0.08
    è¸ŀ
    -0.08
    este
    -0.08
    POSITIVE LOGITS
     Nadu
    0.11
    .argv
    0.10
    人家
    0.09
    ney
    0.09
    mente
    0.09
     اÙĦÙħتØŃدة
    0.09
    缸éĢļ
    0.09
    ision
    0.09
    åħ±åIJĮä½ĵ
    0.09
    untime
    0.08
    Activations Density 0.005%

    No Known Activations