© 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. 51675
    Prev
    Next
    INDEX
    Explanations

    state-owned or state-run 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
    cow
    -0.10
    æĭİ
    -0.09
    ä¸īæľŁ
    -0.09
     season
    -0.09
    åĬ¡å®ŀ
    -0.09
    ibal
    -0.08
    å¾ĭ
    -0.08
    éºĵ
    -0.08
    第ä¸ī次
    -0.08
    æĿµ
    -0.08
    POSITIVE LOGITS
    åĽ½æľī
    0.14
     اÙĦÙħÙħÙĦ
    0.14
    央ä¼ģ
    0.13
    ä¾ĽçĶµåħ¬åı¸
    0.12
    åŀĦæĸŃ
    0.11
    åĽ½ä¼ģ
    0.11
    åĽ½æľīä¼ģä¸ļ
    0.10
    åģļ强
    0.10
    æīĢæľīæĿĥ
    0.10
    åĽ½èµĦ
    0.10
    Activations Density 0.091%

    No Known Activations