© 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. 21260
    Prev
    Next
    INDEX
    Explanations

    animal production and livestock

    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
    åīĭ
    -0.11
    ä¸Ńæŀ¢
    -0.10
    åıijåĬ¨
    -0.10
     Habit
    -0.10
    ä¼IJ
    -0.10
    untime
    -0.09
    é¢Ŀ
    -0.09
    æĸIJ
    -0.09
    /vnd
    -0.09
    ä¾µçķ¥
    -0.09
    POSITIVE LOGITS
    禽
    0.14
    åħ»æ®ĸ
    0.13
    饲åħ»
    0.12
    饲
    0.11
    èĨ»
    0.11
    çķľçī§ä¸ļ
    0.11
    åĬ¨çī©
    0.10
    鸡
    0.10
    è±¢
    0.10
    åĸĤ
    0.10
    Activations Density 0.124%

    No Known Activations