© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10522
    Prev
    Next
    INDEX
    Explanations

    updates and improvements

    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
     пÑĢе
    -0.09
    ä¿Ł
    -0.09
    é¢ĦæĸĻ
    -0.09
    ucher
    -0.09
    ç«Ļåľ¨
    -0.09
    èĦ¸ä¸Ĭ
    -0.09
    ECH
    -0.09
    /native
    -0.09
    æĹIJ
    -0.08
    anford
    -0.08
    POSITIVE LOGITS
    çķ¥æľī
    0.11
    å¢ŀ强äºĨ
    0.10
    å¢ŀåĬłäºĨ
    0.10
     slightly
    0.10
    åĢ¾
    0.10
    说äºĨ
    0.10
    æĶ¹è¿Ľ
    0.09
    åĤ¾
    0.09
    æıIJåįĩäºĨ
    0.09
    æĽ´åħ·
    0.09
    Activations Density 0.081%

    No Known Activations