© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52629
    Prev
    Next
    INDEX
    Explanations

    raid days, boss battle

    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
    对该
    -0.10
    ç½
    -0.09
    ç»į
    -0.09
    å¦ĥ
    -0.09
    éĢĬ
    -0.09
    å©ļåIJİ
    -0.08
    æĽ¿
    -0.08
     Kensington
    -0.08
    jong
    -0.08
     Hyde
    -0.08
    POSITIVE LOGITS
    éĺŁåijĺ们
    0.10
    éĺŁåijĺ
    0.09
    éĩį建
    0.09
    ä¼ļåijĺ
    0.09
    åĽ¢åijĺ
    0.09
    åĽ¢
    0.08
    rectangle
    0.08
    éĻĮçĶŁäºº
    0.08
    Smarty
    0.08
    伤çĹħ
    0.08
    Activations Density 0.017%

    No Known Activations