© 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. 18082
    Prev
    Next
    INDEX
    Explanations

    writ of mandamus

    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
    åĬŁåĬĽ
    -0.09
    åIJŀ
    -0.09
     cork
    -0.09
    çļĦä¸ĢåĪĩ
    -0.09
    赢家
    -0.09
    æĪIJå°±
    -0.09
    çļĦåĪ©çĽĬ
    -0.09
    碲
    -0.09
    ä¹¾
    -0.09
    âĮī
    -0.08
    POSITIVE LOGITS
     xúc
    0.11
    rost
    0.10
    lock
    0.09
    éĥ½å¸Ĥ
    0.09
    ĥģ
    0.09
    身
    0.09
    æ¯ħ
    0.09
    帨
    0.09
    æ³¢çī¹
    0.09
    ths
    0.08
    Activations Density 0.079%

    No Known Activations