© 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. 37111
    Prev
    Next
    INDEX
    Explanations

    jdbc connection driver

    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
    DSA
    -0.10
    éŃģ
    -0.10
    æ·ĩ
    -0.09
    å½¢
    -0.09
    纳æĸ¯
    -0.08
     itemprop
    -0.08
    rens
    -0.08
    packing
    -0.08
    arts
    -0.08
     nicely
    -0.08
    POSITIVE LOGITS
    è¿ŀæİ¥
    0.13
     connection
    0.11
    .getConnection
    0.10
     Connection
    0.10
    ResultSet
    0.10
    æĸ½çŃĸ
    0.10
    .cursor
    0.09
    _connection
    0.09
    驱åĬ¨
    0.09
    è¿Ļå¥Ĺ
    0.09
    Activations Density 0.355%

    No Known Activations