© 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. 20476
    Prev
    Next
    INDEX
    Explanations

    gain or win

    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
    绵
    -0.10
    æµģæĺŁ
    -0.09
    æĸĹ
    -0.09
    ç¾ļ
    -0.08
    éĤ£å¤©
    -0.08
    éħ¥
    -0.08
    jer
    -0.08
     enumerable
    -0.08
    Enumerable
    -0.08
     select
    -0.08
    POSITIVE LOGITS
    åıĹçĽĬ
    0.14
    çļĦåĪ©çĽĬ
    0.11
     benefit
    0.11
    裨
    0.10
    æĦ¿
    0.10
    好å¤Ħ
    0.10
    benef
    0.10
    é¡ĺ
    0.10
     trông
    0.10
    å¾ħ
    0.09
    Activations Density 0.035%

    No Known Activations