© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 57440
    Prev
    Next
    INDEX
    Explanations

    legal and financial decisions

    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
    ä¹łæĥ¯
    -0.10
    кеÑĢ
    -0.10
    鬣
    -0.10
    åĩĨ
    -0.10
    ote
    -0.09
    æīĵå¼ĢäºĨ
    -0.09
    ä¹Ŀåįģ
    -0.08
    åħ¥ãĤĬ
    -0.08
    abit
    -0.08
    åħ¥æĪ·
    -0.08
    POSITIVE LOGITS
    æİĪæĿĥ
    0.12
    代çIJĨ
    0.11
    proxy
    0.10
    代åĬŀ
    0.10
    å§Ķæīĺ
    0.10
    -proxy
    0.10
    åĬŀ
    0.09
    代çIJĨ人
    0.09
    ronics
    0.09
    ç¥Ŀ
    0.09
    Activations Density 0.014%

    No Known Activations