© 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. 9146
    Prev
    Next
    INDEX
    Explanations

    assistants, department, employees, staff, ladies, supporters, team

    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
    èĵ¼
    -0.11
    æĸ°ä¸Ģè½®
    -0.10
    主人
    -0.10
    çĪ·çĪ·
    -0.10
     Finn
    -0.10
    大人
    -0.09
    æ´µ
    -0.09
    بس
    -0.09
    çĺģ
    -0.09
    éĽĩ主
    -0.09
    POSITIVE LOGITS
    帮ä»ĸ
    0.11
    ç°ĩ
    0.11
    åĬ©æīĭ
    0.10
    hip
    0.10
    åĬ©
    0.10
    ä¸ĭå±ŀ
    0.09
    éĻª
    0.09
     помоÑī
    0.09
    æīĭä¸ĭ
    0.09
    å®łçĪ±
    0.09
    Activations Density 0.092%

    No Known Activations