© 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. 61386
    Prev
    Next
    INDEX
    Explanations

    manufacturing or production sites

    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
    秣
    -0.11
    å¼ĥ
    -0.10
    åģ¥
    -0.10
    æľ¬ç½ijç«Ļ
    -0.10
    éģĹ
    -0.10
     напÑĢавлен
    -0.10
    éģ£
    -0.09
    hipster
    -0.09
    æ±ľ
    -0.09
    reen
    -0.09
    POSITIVE LOGITS
    ç»Ħè£ħ
    0.17
    åĪ¶éĢł
    0.14
     manufacturing
    0.12
     manufacture
    0.11
     manufacturers
    0.11
    manufact
    0.11
    鼶éĥ¨ä»¶
    0.11
    è£ħéħį
    0.11
    åĪ¶éĢłåķĨ
    0.11
    åİĤ
    0.10
    Activations Density 0.095%

    No Known Activations