© 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. 18780
    Prev
    Next
    INDEX
    Explanations

    vehicle repair and tires

    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
    ढ
    -0.10
    levant
    -0.10
    让人们
    -0.09
    åįİ润
    -0.09
    æ½®æµģ
    -0.09
    ç²īç¢İ
    -0.09
    æĮģæľī人
    -0.08
    виÑĤ
    -0.08
    /linux
    -0.08
     lev
    -0.08
    POSITIVE LOGITS
    汽车
    0.11
    æľºåĬ¨è½¦
    0.10
    æ±½
    0.10
    ä¸ĩåħ¬éĩĮ
    0.10
    车主
    0.10
    ä¿Ŀåħ»
    0.10
    车è¾Ĩ
    0.10
    æ±½è»Ĭ
    0.09
    轿车
    0.09
    åĸĩåıŃ
    0.09
    Activations Density 0.118%

    No Known Activations