© 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. 37319
    Prev
    Next
    INDEX
    Explanations

    according to

    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
     tri
    -0.08
    ä¸į对
    -0.08
     NASA
    -0.07
    槽
    -0.07
    åĬŀåħ¬æ¥¼
    -0.07
    èĩªèIJ¥
    -0.07
    ds
    -0.07
     Netflix
    -0.07
    -P
    -0.07
     Google
    -0.07
    POSITIVE LOGITS
    çļĦéľĢæ±Ĥ
    0.11
     ÐĿи
    0.10
    ILT
    0.10
    åij¨åĪĬ
    0.10
    ä¸ļçķĮ
    0.10
    大åĴĸ
    0.10
    åIJĦçľģ
    0.10
    è¡Įä¸ļåıijå±ķ
    0.09
    è¿Ļ个è¡Įä¸ļ
    0.09
    æĦŁåħ´è¶£
    0.09
    Activations Density 0.230%

    No Known Activations