© 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. 3448
    Prev
    Next
    INDEX
    Explanations

    improve efficiency and reduce costs

    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
    æĺ¯æľĢ好çļĦ
    -0.09
    -widgets
    -0.09
    å¾Īæ·±
    -0.08
    åIJ¬è¯¾
    -0.08
    åĽ½åľŁ
    -0.08
    å²ĺ
    -0.08
    åķľ
    -0.08
    ä»įçĦ¶æĺ¯
    -0.08
    çļĦä¹łæĥ¯
    -0.08
    addListener
    -0.08
    POSITIVE LOGITS
    çľģ
    0.10
    欺è¯Ī
    0.09
    åĩıå°ij
    0.09
     Fraud
    0.09
    èĢ½è¯¯
    0.09
    æĽ´å¿«
    0.08
    æĸ¹ä¾¿
    0.08
    以åīį
    0.08
    便åĪ©
    0.08
    çIJĨ
    0.08
    Activations Density 0.111%

    No Known Activations