© 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. 20497
    Prev
    Next
    INDEX
    Explanations

    first time in years

    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
    rema
    -0.09
    西åĮĹ
    -0.09
    ä¹ŁçŁ¥éģĵ
    -0.08
    å°¤åħ¶
    -0.08
    URING
    -0.08
    _Ptr
    -0.08
    éľĦ
    -0.08
    ä½»
    -0.08
     reco
    -0.08
     Rolled
    -0.08
    POSITIVE LOGITS
    人éĹ´
    0.08
    ä¸Ķ
    0.08
    许ä¹ħ
    0.08
    bat
    0.08
    èĥľè´Ł
    0.08
    沧
    0.08
    æĮ¹
    0.08
    æľīæīĢ
    0.08
    æĪĸèĢħ说
    0.08
    被迫
    0.08
    Activations Density 0.019%

    No Known Activations