© 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. 10562
    Prev
    Next
    INDEX
    Explanations

    invention relates to processes

    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
    ocator
    -0.10
    avy
    -0.10
    è¦ģåģļ好
    -0.09
    å¬ĸ
    -0.09
    ä¸Ģéģį
    -0.09
    èĥ½æ»¡è¶³
    -0.09
    使ä¹ĭ
    -0.09
    æľīæīĢ
    -0.09
    åı¯æł¹æį®
    -0.08
    æĹłçĸij
    -0.08
    POSITIVE LOGITS
    驯
    0.09
    æľ´å®ŀ
    0.09
     sharpen
    0.09
    åİĦ
    0.09
    æŁ¥çľĭæĽ´å¤ļ
    0.09
    èĹľ
    0.09
    zer
    0.08
    EUR
    0.08
    å¤ļä½į
    0.08
    eur
    0.08
    Activations Density 0.218%

    No Known Activations