© 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. 52867
    Prev
    Next
    INDEX
    Explanations

    building structures

    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
    糧
    -0.10
     ÑģкаÑĩ
    -0.10
    è¾IJ
    -0.09
    æĽ´å¥½
    -0.09
    è¿Ļåıª
    -0.09
    工人
    -0.09
    ebra
    -0.09
    马æĭī
    -0.09
    ular
    -0.09
    æ±Ĺæ°´
    -0.08
    POSITIVE LOGITS
    ä¸Ģä¸ĸ
    0.10
    æĿIJè´¨
    0.09
    æľŁåĪĬ
    0.09
    ä¸įåĪ°ä½į
    0.09
     shadow
    0.09
    oto
    0.09
    çķĮ
    0.09
    éĩį
    0.09
    åģ·
    0.09
    íĻ©
    0.08
    Activations Density 0.076%

    No Known Activations