© 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. 51845
    Prev
    Next
    INDEX
    Explanations

    educational technology

    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
    çĻ¾ä¸ĩ
    -0.08
    æĮ¹
    -0.08
    ubi
    -0.07
    éħ¬
    -0.07
     intros
    -0.07
    è¡Įä¸ļåĨħ
    -0.07
    çī©ä¸ļ管çIJĨ
    -0.07
    Assertions
    -0.07
    æĪªåĽ¾
    -0.07
    ä¿ĿçķĻ
    -0.07
    POSITIVE LOGITS
    让åѦçĶŁ
    0.18
    åѦçĶŁçļĦ
    0.18
    åѦçĶŁä»¬
    0.16
    åѦçĶŁ
    0.15
     students
    0.14
    让ä»ĸ们
    0.14
    çļĦåѦçĶŁ
    0.14
    对åѦçĶŁ
    0.13
    åѸçĶŁ
    0.13
    Students
    0.12
    Activations Density 0.272%

    No Known Activations