© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37365
    Prev
    Next
    INDEX
    Explanations

    emergence of technological advancement

    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
    建åħļ
    -0.11
    æľªæĿ¥åıijå±ķ
    -0.10
    转载
    -0.09
    ç¿Ķ
    -0.09
    IDD
    -0.08
    æĻļå¹´
    -0.08
    天èĬ±æĿ¿
    -0.08
    åĴĮæľįåĬ¡
    -0.08
    éĢīåĿĢ
    -0.08
    tpl
    -0.08
    POSITIVE LOGITS
    æīĢè°ĵçļĦ
    0.10
    æļĤç¼ĵ
    0.10
    æĴŃ
    0.10
    è¿Ļç§įæĸ¹æ³ķ
    0.09
    以ä¾Ĩ
    0.09
    anness
    0.09
    è¿Ļ两ç§į
    0.09
    线ä¸Ĭ
    0.08
    æİĮ
    0.08
    åĽĽçº§
    0.08
    Activations Density 0.110%

    No Known Activations