© 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. 37090
    Prev
    Next
    INDEX
    Explanations

    secret for staying young

    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
    umo
    -0.12
    æĿ¥åĪ°äºĨ
    -0.11
    空åīį
    -0.10
    æĢ§åĴĮ
    -0.09
     unfinished
    -0.09
    éĢĤåIJĪèĩªå·±
    -0.09
    ç»ıåħ¸çļĦ
    -0.09
    è·Ĺ
    -0.09
    亲身
    -0.09
    绨
    -0.09
    POSITIVE LOGITS
    æ¯ĶæĪij
    0.17
    缸æ¯Ķä¹ĭä¸ĭ
    0.11
    人家
    0.09
    Cli
    0.09
    侯
    0.09
    æ¯ı天
    0.09
    对æĪijæĿ¥è¯´
    0.09
    åĢĻ
    0.09
    对çħ§
    0.08
     Alvarez
    0.08
    Activations Density 0.109%

    No Known Activations