© 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. 53999
    Prev
    Next
    INDEX
    Explanations

    military campaign, search, journey, adventure

    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
    æĺı
    -0.10
    æľīäºĨ
    -0.09
     dane
    -0.09
     McCorm
    -0.09
    éĶµ
    -0.09
    家éŨåı£
    -0.08
     Fence
    -0.08
    .Make
    -0.08
    è¿Īåĩº
    -0.08
    UF
    -0.08
    POSITIVE LOGITS
    äºĨä¸Ģç³»åĪĹ
    0.13
    ä¸Ģç³»åĪĹ
    0.11
    ç³»åĪĹ
    0.09
    æĦı大
    0.09
     Born
    0.09
    åIJį为
    0.09
    resh
    0.09
    æĹ¢è¦ģ
    0.08
     extensive
    0.08
    ä¼ļåIJĮ
    0.08
    Activations Density 0.272%

    No Known Activations