© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 9398
    Prev
    Next
    INDEX
    Explanations

    which introduces a subordinate clause

    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¸Ĺำà¸ģาร
    -0.10
    èµĸ
    -0.10
    æĻ¯å¾·
    -0.09
    åģļåΰ
    -0.09
    æĥķ
    -0.09
    å§Ĭ妹
    -0.09
    å¨ĺå¨ĺ
    -0.09
    åIJķ
    -0.09
    éªĽ
    -0.08
    ç»ķ
    -0.08
    POSITIVE LOGITS
    æľīçļĦ人
    0.10
    which
    0.09
    çͱ
    0.09
    bol
    0.08
    Anc
    0.08
     which
    0.08
     Gan
    0.08
     favourites
    0.08
    称为
    0.08
     scholarship
    0.08
    Activations Density 0.141%

    No Known Activations