© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9614
    Prev
    Next
    INDEX
    Explanations

    tribal affiliations and clans

    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
     Exped
    -0.11
    人éĢł
    -0.10
    å¿ĥè¡Ģ
    -0.10
     اÙĦتج
    -0.09
    éĶ¦æłĩ
    -0.09
    人éĹ´
    -0.09
    è¯ģåĪ¸äº¤æĺĵ
    -0.09
     Prague
    -0.09
    é¦Ĩ
    -0.09
    æķıæį·
    -0.09
    POSITIVE LOGITS
     clan
    0.10
    乡
    0.10
     clans
    0.09
    姻
    0.09
     arist
    0.09
     Clan
    0.09
    ä¼łç»ŁçļĦ
    0.09
    å·´åŁº
    0.08
    æŃĥ
    0.08
    éĦī
    0.08
    Activations Density 0.101%

    No Known Activations