© 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. 19793
    Prev
    Next
    INDEX
    Explanations

    world, global, human, government, population

    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
    æĪį
    -0.10
    对æīĭ
    -0.10
    她们
    -0.10
    åĽ½æĥħ
    -0.10
    该åİ¿
    -0.09
    è¡ĹåĮº
    -0.09
    åĩºåı£
    -0.09
    çł¾
    -0.09
    è¿ĻæĶ¯
    -0.09
     Shed
    -0.09
    POSITIVE LOGITS
    人类
    0.15
    人é¡ŀ
    0.11
     mankind
    0.11
    åħ¨çIJĥ
    0.11
    åľ°çIJĥ
    0.11
    æŃ¥åħ¥
    0.10
    .Global
    0.10
    Global
    0.10
    åħ¨ä¸ĸçķĮ
    0.10
     Global
    0.10
    Activations Density 0.148%

    No Known Activations