© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9742
    Prev
    Next
    INDEX
    Explanations

    emergency response, treatment, meetings

    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
    èĭ¥æľī
    -0.10
    å¯ĵæĦı
    -0.10
    å¹¼ç¨ļ
    -0.09
    寡
    -0.08
    çĽĬ
    -0.08
    æľĢåĪĿ
    -0.08
    åĪĿå¿ĥ
    -0.08
    rar
    -0.08
    maj
    -0.08
    obic
    -0.08
    POSITIVE LOGITS
    æĬ¢éĻ©
    0.12
    æĮ½æķij
    0.12
    æĬ¢æķij
    0.11
    æĬ¢
    0.11
    æIJ¶
    0.11
    ä¸įåıĬ
    0.11
    赶赴
    0.11
    æķijåij½
    0.11
    æĢ¥å¿Ļ
    0.10
    æĿ¥ä¸´
    0.10
    Activations Density 0.052%

    No Known Activations