© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 30727
    Prev
    Next
    INDEX
    Explanations

    Christian denominations and church

    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
    æł·åŃIJ
    -0.09
    ç¦ıå¾·
    -0.09
    ç¼ĸåī§
    -0.08
    窣
    -0.08
     elk
    -0.08
    çĴĭ
    -0.08
     пÑĢоÑģ
    -0.08
    åºĵéĩĮ
    -0.08
     Bruno
    -0.08
    decay
    -0.08
    POSITIVE LOGITS
    人士
    0.10
    åľ¨æķ´ä¸ª
    0.09
    åIJĪèµĦ
    0.09
    èģĶåIJĪä¼ļ
    0.09
    UUID
    0.09
    太太
    0.09
    éħIJ
    0.08
    å¾Ĵ
    0.08
    æ°ĽåĽ´
    0.08
    nex
    0.08
    Activations Density 0.036%

    No Known Activations