© 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. 55134
    Prev
    Next
    INDEX
    Explanations

    PCI compliance 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
    aget
    -0.10
    оÑĢо
    -0.10
    éĺ¡
    -0.09
     Preston
    -0.09
    ä¸īä½įä¸Ģä½ĵ
    -0.09
    å¼ĢæĿ¥
    -0.09
    .pivot
    -0.09
    亮
    -0.09
    çĿļ
    -0.09
    .cgi
    -0.08
    POSITIVE LOGITS
     Clement
    0.10
    æķıæĦŁ
    0.09
    亹
    0.09
    PCI
    0.09
     PCI
    0.08
    åĶ¿
    0.08
    åĢĴåľ¨
    0.08
     sát
    0.08
    åĮ»çĸĹåį«çĶŁ
    0.08
    jang
    0.08
    Activations Density 0.051%

    No Known Activations