© 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. 7682
    Prev
    Next
    INDEX
    Explanations

    garbage collection, memory management, collecting objects

    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
    ä¸ĢåŃĹ
    -0.10
    æĤ¬å¿µ
    -0.09
    æĭĹ
    -0.09
    æł©
    -0.09
    åģı
    -0.09
    åİļ
    -0.09
    åİļåİļ
    -0.08
    .enterprise
    -0.08
    åĪĥ
    -0.08
    ç»Ĩç»Ĩ
    -0.08
    POSITIVE LOGITS
    æ¸ħçIJĨ
    0.15
    æİĴæ¯Ĵ
    0.14
    æ¸ħæ´ģ
    0.12
    åĩĢåĮĸ
    0.12
    æ¸ħéĻ¤
    0.11
    æīĵæī«
    0.11
     gc
    0.11
    (gc
    0.11
    .gc
    0.11
    æ¸ħæī«
    0.11
    Activations Density 0.095%

    No Known Activations