© 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. 57011
    Prev
    Next
    INDEX
    Explanations

    government agencies and regulations

    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
    ç©¿æĪ´
    -0.09
    éĢ¯
    -0.08
    ä¹ī
    -0.08
    prints
    -0.08
    BaseContext
    -0.08
    æĿ³
    -0.08
    çijķ
    -0.08
    Ùħد
    -0.08
    å¸ħæ°Ķ
    -0.08
    ç»ī
    -0.08
    POSITIVE LOGITS
    认åı¯
    0.14
    æĦıä¹īä¸ĬçļĦ
    0.13
    è¦ģæ±Ĥ
    0.11
    è§Ħå®ļçļĦ
    0.11
    ä¸¥æł¼çļĦ
    0.09
     tán
    0.09
    æłĩåĩĨ
    0.09
    æľĢé«ĺçļĦ
    0.09
    å¾Ĺèµ·
    0.09
    ToLocal
    0.09
    Activations Density 0.303%

    No Known Activations