© 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. 21672
    Prev
    Next
    INDEX
    Explanations

    military company designations

    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
    ä»ĺè´¹
    -0.09
    ä¸ĢæŶ
    -0.09
    æ²»å®ī
    -0.09
     деÑĤÑģк
    -0.09
    èѦæĸ¹
    -0.09
    éħ½
    -0.09
    对æѤ
    -0.09
    é¢Ĭ
    -0.09
    京津
    -0.09
    æµ·çĽĹ
    -0.09
    POSITIVE LOGITS
    çıŃ
    0.10
    æĬł
    0.09
    ä¼Ļä¼´
    0.09
    å¼ŁåħĦ
    0.09
    äºŃ
    0.09
    æīª
    0.08
    èıľé¸Ł
    0.08
     Hermes
    0.08
    çıŃéķ¿
    0.08
    éĺŁåijĺ
    0.08
    Activations Density 0.133%

    No Known Activations