© 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. 56155
    Prev
    Next
    INDEX
    Explanations

    birth year

    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
    åıijçĶŁçļĦ
    -0.10
    вол
    -0.10
    ä¼ļåıijçĶŁ
    -0.09
    京åŁİ
    -0.09
    çļĦåģļæ³ķ
    -0.09
    åıijçĶŁ
    -0.09
    æŶæķĪ
    -0.09
    åIJ
    -0.09
    æ»
    -0.08
    åįĪ
    -0.08
    POSITIVE LOGITS
    åĩºçĶŁäºİ
    0.09
    otec
    0.09
    xmm
    0.09
    æīĴ
    0.08
    ä¸ĸçķĮä¸Ĭ
    0.08
    è¿Ļä¸ĢåĪĩ
    0.08
     Че
    0.08
     bä
    0.08
    prech
    0.08
    çĪ¶æ¯į
    0.08
    Activations Density 0.241%

    No Known Activations