© 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
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37149
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    羡
    -0.08
    åĮ¿
    -0.08
    件
    -0.08
    è¦ģ注æĦı
    -0.08
    istica
    -0.08
    nect
    -0.08
    åł¤
    -0.08
     Cod
    -0.07
    侯
    -0.07
    ç»Ĩ
    -0.07
    POSITIVE LOGITS
    lander
    0.10
    gable
    0.10
    主任
    0.09
     thuáºŃn
    0.09
    åĽłä¸ºåľ¨
    0.09
    交ä¼ļ
    0.09
    _Group
    0.09
    èħ´
    0.09
    æĶ¾æīĭ
    0.09
    .au
    0.09
    Activations Density 0.000%

    No Known Activations