© 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. 36918
    Prev
    Next
    INDEX
    Explanations

    Donald Trump and related entities

    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
    bsd
    -0.10
    çݳ
    -0.09
    æĽ´æľī
    -0.09
    太平æ´ĭ
    -0.08
    ä¼Ļ
    -0.08
    åѱ
    -0.08
    anga
    -0.08
    ÅĽci
    -0.08
    æĬ±ä½ı
    -0.08
    鸦
    -0.08
    POSITIVE LOGITS
    Trump
    0.11
     Trump
    0.10
    Donald
    0.10
    åĽ½åĬ¡
    0.10
    ç¾½
    0.10
    åıŁ
    0.09
    .loader
    0.09
     BIN
    0.09
     Blasio
    0.09
     FOOT
    0.09
    Activations Density 0.257%

    No Known Activations