© 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. 52058
    Prev
    Next
    INDEX
    Explanations

    spin-echo sequence

    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
    åľ¨äº¬
    -0.10
    ä¸Ģä¸Ŀ
    -0.10
    sworth
    -0.10
    itarian
    -0.09
    ä¸ĢèĦ¸
    -0.09
    æıĨ
    -0.09
    .mods
    -0.09
    åľ¨ä»ĸ
    -0.09
    åģıåģı
    -0.09
    æľ´ç´ł
    -0.09
    POSITIVE LOGITS
    åĢĴ
    0.11
    Ñģоб
    0.09
    é¢ł
    0.09
    vant
    0.08
    iq
    0.08
    ough
    0.08
    аÑĨион
    0.08
     REV
    0.08
    æĹ¢
    0.08
    æĢ¡
    0.08
    Activations Density 0.001%

    No Known Activations