© 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. 37210
    Prev
    Next
    INDEX
    Explanations

    unique

    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
    ä¸ĢäºĮ
    -0.09
    ç»Ħ建
    -0.09
    olini
    -0.09
    igrams
    -0.09
    æīĵæī®
    -0.09
    (COM
    -0.08
     Gund
    -0.08
    _DIG
    -0.08
    ç¢ĵ
    -0.08
    åįİ侨
    -0.08
    POSITIVE LOGITS
    èĪ¬çļĦ
    0.10
     (?)
    0.10
    èĪ¬
    0.09
    èµĤ
    0.09
    æĥħåĨµä¸ĭ
    0.09
     khả
    0.09
    çļĦåľ°ä½į
    0.08
     Breed
    0.08
    çļĦéŃħåĬĽ
    0.08
    çIJ¼
    0.08
    Activations Density 0.017%

    No Known Activations