© 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. 52256
    Prev
    Next
    INDEX
    Explanations

    military command and leadership

    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
    æĭ¿äºĨ
    -0.09
    姿åĬ¿
    -0.08
     scand
    -0.08
    åºŁ
    -0.08
    榫
    -0.08
    趴
    -0.08
     extortion
    -0.08
    çŃij
    -0.08
    arrass
    -0.08
    éģĵ士
    -0.08
    POSITIVE LOGITS
    æĮĩæĮ¥
    0.22
    åı¸ä»¤
    0.15
    åij½ä»¤
    0.15
    çİĩé¢Ĩ
    0.14
    é¢Ĩ导ä¸ĭ
    0.14
     command
    0.13
    é¢Ĩ导
    0.13
    亲èĩª
    0.12
    绣é¢Ĩ
    0.12
    带é¢Ĩ
    0.12
    Activations Density 0.093%

    No Known Activations