© 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. 5527
    Prev
    Next
    INDEX
    Explanations

    network configuration and services

    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
    åĩĿèģļåĬĽ
    -0.10
    é¢Ĩ导人
    -0.10
    çłĶ究åijĺ
    -0.09
    éĩıåĮĸ
    -0.09
    æĪªåĽ¾
    -0.08
    æĸ°åĬł
    -0.08
    ç½ijåıĭ们
    -0.08
    æĬ±åĽ¢
    -0.08
    çIJĨ论
    -0.08
     theoretical
    -0.08
    POSITIVE LOGITS
    裾
    0.09
    ä»ĬæĹ¥ãģ¯
    0.09
    篷
    0.08
    秫
    0.08
    æĭ¾
    0.08
    Mom
    0.08
    å§Ķç»Ħç»ĩ
    0.07
     traversal
    0.07
     Tanz
    0.07
    æ£ļ
    0.07
    Activations Density 0.384%

    No Known Activations