© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 31186
    Prev
    Next
    INDEX
    Explanations

    sale, auction, bidding

    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
    éĽĩä½£
    -0.10
    ç£ķ
    -0.10
    第ä¸ī代
    -0.09
    éķĶ
    -0.09
    esi
    -0.09
    绵
    -0.09
    FRING
    -0.09
    èĪģ
    -0.08
    åģļåĩº
    -0.08
     mouths
    -0.08
    POSITIVE LOGITS
    æĭįåįĸ
    0.14
     Auction
    0.13
     auction
    0.12
     bidding
    0.12
    æĬ¢
    0.12
    æĭĽæłĩ
    0.11
     auctions
    0.11
    auction
    0.11
    äºĨä¸Ģæī¹
    0.11
    ç«ŀä»·
    0.11
    Activations Density 0.056%

    No Known Activations