© 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. 20540
    Prev
    Next
    INDEX
    Explanations

    free software; redistribute and/or modify

    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
    à¤ł
    -0.10
    ascar
    -0.09
    åĮ¹
    -0.09
    æĪIJ年人
    -0.09
    æĺ¼å¤ľ
    -0.09
     cadre
    -0.09
    IGO
    -0.09
    ä¸įæŃ»
    -0.09
    killer
    -0.09
    æĬĬæīĭ
    -0.09
    POSITIVE LOGITS
    é¬ĥ
    0.10
    è¿ĺä¸įå¤Ł
    0.09
     siden
    0.08
    ç«Ļç«ĭ
    0.08
    åŤ
    0.08
    社ä¼ļåĮĸ
    0.08
    èĥľè´Ł
    0.08
    edm
    0.08
     breaking
    0.08
    ä¼´ä¾£
    0.08
    Activations Density 0.010%

    No Known Activations