© 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. 7829
    Prev
    Next
    INDEX
    Explanations

    BP or B.P

    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
    esse
    -0.09
    æĬ¼ãģĹ
    -0.09
    inary
    -0.09
    åĮ£
    -0.09
    é¹°
    -0.09
    OUS
    -0.09
    spo
    -0.09
    esk
    -0.09
    éĵ¼
    -0.09
    大大æıIJé«ĺ
    -0.08
    POSITIVE LOGITS
    ä¸Ģ个å¤ļ
    0.09
    æįº
    0.08
    æ¶ķ
    0.08
     paternal
    0.08
    æģ¢
    0.08
    æĮīçħ§
    0.08
    æģ¢å¤į
    0.08
    å°½åĬĽ
    0.08
     lược
    0.08
    netinet
    0.08
    Activations Density 0.003%

    No Known Activations