© 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. 33051
    Prev
    Next
    INDEX
    Explanations

    transaction management

    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
    åݨ
    -0.10
    åŃ£èĬĤ
    -0.10
    ijľ
    -0.09
    æĸĩ娱
    -0.09
    بدÙĦ
    -0.09
    å²ģæŶ
    -0.08
    ãĤĴãģĬ
    -0.08
    éģ¥æݧ
    -0.08
    bios
    -0.08
     sl
    -0.08
    POSITIVE LOGITS
     transaction
    0.13
    交æĺĵ
    0.11
    transaction
    0.11
     Transaction
    0.11
    _transaction
    0.11
    .transaction
    0.11
    .Transaction
    0.10
     transactions
    0.10
    Transaction
    0.10
    äºĭåĬ¡
    0.10
    Activations Density 0.086%

    No Known Activations