© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37088
    Prev
    Next
    INDEX
    Explanations

    may not

    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
     ÑĤеÑħнологии
    -0.08
    åı¯ä»¥èİ·å¾Ĺ
    -0.08
    ç§ijåѦæĬĢæľ¯
    -0.08
     Academy
    -0.08
    oted
    -0.08
    val
    -0.08
    åĽ½åĨħå¸Ĥåľº
    -0.08
    使æĪij
    -0.08
    æ¾Ī
    -0.08
    使ä¹ĭ
    -0.08
    POSITIVE LOGITS
    å¤Ķ
    0.10
     беÑģ
    0.09
    ç¥İ
    0.09
    ầy
    0.09
    å©¿
    0.09
    ä¸įå®Į
    0.09
    itas
    0.09
    è¿Ļåĩłä¸ª
    0.09
    æĸĭ
    0.09
    å²ĺ
    0.08
    Activations Density 0.028%

    No Known Activations