© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 1626
    Prev
    Next
    INDEX
    Explanations

    secretary of War

    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
     zer
    -0.09
    åľ¹
    -0.09
    zer
    -0.09
    èįł
    -0.09
    åħ¥æĪ·
    -0.09
    åĹ½
    -0.09
    æĹı
    -0.09
    赶
    -0.08
     dut
    -0.08
    çĶ·å¥³
    -0.08
    POSITIVE LOGITS
     Roose
    0.10
    æĸ°ä¸ī
    0.10
    usal
    0.09
    åĽ½åĬ¡
    0.09
    ä¿Ń
    0.09
    æĸĹ
    0.09
    å´¤
    0.09
    åĬ¡
    0.09
    温åĴĮ
    0.08
    缸åħ³æĶ¿çŃĸ
    0.08
    Activations Density 0.108%

    No Known Activations