© 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. 31133
    Prev
    Next
    INDEX
    Explanations

    items for auction or sale

    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
    HC
    -0.09
    sap
    -0.09
    æķ·
    -0.09
    åıĸæļĸ
    -0.08
    æĻ®æĥł
    -0.08
    éĽª
    -0.08
    hal
    -0.08
    ApplicationBuilder
    -0.08
     اÙĦÙħÙĪا
    -0.08
    agine
    -0.08
    POSITIVE LOGITS
    æĭįåįĸ
    0.20
     auction
    0.16
     Auction
    0.15
    auction
    0.13
     auctions
    0.12
    åħ¬è¯ģ
    0.12
    ãĤªãĥ¼
    0.11
    ç«ŀä»·
    0.11
    转让
    0.11
    æĪIJ交
    0.10
    Activations Density 0.116%

    No Known Activations