© 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. 63326
    Prev
    Next
    INDEX
    Explanations

    amount of resources

    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
    å¼ĢåıijèĢħ
    -0.10
    ä¸Ģå¹ķ
    -0.09
    ä¸įåºĶ该
    -0.09
    ä¹ŁåIJĮæł·
    -0.09
    æľĢ大çļĦ
    -0.09
    ä¸Ģ群
    -0.09
    çī§
    -0.09
    æĪ¿
    -0.09
    æľīä¸Ģå®ļçļĦ
    -0.09
    essler
    -0.09
    POSITIVE LOGITS
     detail
    0.09
    åľ¨è¿Ļ个
    0.08
    çºł
    0.08
    ÑĤол
    0.08
     acre
    0.08
     involved
    0.08
    variation
    0.08
    éĽĨä¸Ńåľ¨
    0.08
     Pron
    0.08
    æŀ
    0.08
    Activations Density 0.154%

    No Known Activations