© 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. 8843
    Prev
    Next
    INDEX
    Explanations

    start of proper nouns and abbreviations

    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
    itore
    -0.10
    çĭŃ
    -0.09
    aired
    -0.09
    åŃIJå¼Ł
    -0.08
    indle
    -0.08
     ÙħÙĨت
    -0.08
    ä¿Ł
    -0.08
    æ¹ĵ
    -0.08
    _Module
    -0.08
    æ³¼
    -0.08
    POSITIVE LOGITS
    ernet
    0.10
    matic
    0.10
    çłĶåĪ¶
    0.09
    æĿijåŃIJ
    0.09
    ä»ĬçĶŁ
    0.08
    alytics
    0.08
    adian
    0.08
    åijĥ
    0.08
     ark
    0.08
    çŃĸ
    0.08
    Activations Density 0.501%

    No Known Activations