© 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. 37409
    Prev
    Next
    INDEX
    Explanations

    military service personnel

    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
    溯
    -0.09
    mitt
    -0.08
    cker
    -0.08
    -mask
    -0.08
    аб
    -0.08
    éĺ²åį«
    -0.08
    èĩªçĦ¶
    -0.08
    å¯Įè£ķ
    -0.08
    bundle
    -0.08
    ODO
    -0.08
    POSITIVE LOGITS
    æľīæľŁ
    0.10
    è¿Ł
    0.09
    æľį
    0.09
    ople
    0.09
     Buzz
    0.09
    å¤ĸæĿ¥
    0.09
    ç´¯äºĨ
    0.09
    æIJ½
    0.09
    æ¯ĭ
    0.09
    æĵ¦
    0.09
    Activations Density 0.025%

    No Known Activations