© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 52178
    Prev
    Next
    INDEX
    Explanations

    American historical figures and places

    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
    念头
    -0.10
    æ·¡åĮĸ
    -0.10
    ipes
    -0.10
     ÑįкÑģ
    -0.10
    çݰ任
    -0.09
    æ®ī
    -0.09
    ä»Ģä¹Īäºĭæĥħ
    -0.09
    å¸Į
    -0.09
    esz
    -0.09
     ÑĥÑģловиÑı
    -0.09
    POSITIVE LOGITS
    .dtype
    0.09
    çĪ·
    0.09
    ays
    0.09
     Barton
    0.08
     DEAL
    0.08
    åŃĹåı·
    0.08
    æĪIJé¾Ļ
    0.08
    Gear
    0.08
    etch
    0.08
    icc
    0.08
    Activations Density 0.067%

    No Known Activations