© 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. 39532
    Prev
    Next
    INDEX
    Explanations

    humanitarian aid and children

    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
    对èĩªå·±
    -0.09
    ä¾®
    -0.08
    æIJŀ
    -0.08
    驾
    -0.08
    ubb
    -0.08
     toler
    -0.08
    ignum
    -0.08
    æĬĬèĩªå·±çļĦ
    -0.08
    éħĴ
    -0.08
     RFC
    -0.08
    POSITIVE LOGITS
    åĩĨåħ¥
    0.10
    çģ¾åĮº
    0.10
    éĹª
    0.09
    éĹªåħī
    0.09
    æĭ£
    0.09
    è¡Ģ液循çݯ
    0.09
    èIJ¥åľ°
    0.09
     flash
    0.09
    æķijçģ¾
    0.09
    ä¸Ģç«Ļ
    0.09
    Activations Density 0.112%

    No Known Activations