© 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. 20734
    Prev
    Next
    INDEX
    Explanations

    scientific theories and evolution

    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
    zek
    -0.09
    ä¸įç»ıæĦı
    -0.09
    èªĵ
    -0.09
    笨
    -0.09
    목
    -0.09
    饵
    -0.09
    èĭ¦éļ¾
    -0.09
     erg
    -0.08
    ä¸Ģç§Ĵ
    -0.08
    å¯ĵæĦı
    -0.08
    POSITIVE LOGITS
    allo
    0.10
    è¾¾å°Ķ
    0.10
    éĤĢ
    0.09
    æĤ¨çļĦåŃ©åŃIJ
    0.09
    Accepted
    0.09
    çĶŁçī©åѦ
    0.09
    .printf
    0.08
    оде
    0.08
    éĻĤ
    0.08
    æĶ¸
    0.08
    Activations Density 0.057%

    No Known Activations