© 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. 11433
    Prev
    Next
    INDEX
    Explanations

    welding or soldering components

    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
    åĮ¡
    -0.12
    .setAction
    -0.11
    é¢Ĺ
    -0.10
    EGA
    -0.10
    Cascade
    -0.10
    æıļ
    -0.09
    箪
    -0.09
     "('
    -0.09
    秣
    -0.09
    é£ı
    -0.09
    POSITIVE LOGITS
    çĦĬ
    0.16
    çĦĬæİ¥
    0.14
     weld
    0.12
     welding
    0.11
     Weld
    0.10
    åĨ¶éĩij
    0.09
    æ¨¡æł·
    0.09
     solder
    0.09
    å·¥ä¼ļ
    0.09
    ä¸įåIJĪæł¼
    0.09
    Activations Density 0.100%

    No Known Activations