© 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. 8123
    Prev
    Next
    INDEX
    Explanations

    names of people and financial entities

    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
    oland
    -0.10
    åĽĽæĸ¹
    -0.10
    æģ¢
    -0.09
    lest
    -0.09
    çĽ
    -0.09
    ç«ŀäºī
    -0.08
    acier
    -0.08
    otype
    -0.08
    éĢļçŁ¥
    -0.08
     lit
    -0.08
    POSITIVE LOGITS
    ä¸į说
    0.11
    ç»ħ
    0.10
     fri
    0.09
    çŃīæ´»åĬ¨
    0.09
     hin
    0.08
    æķ·
    0.08
    ologue
    0.08
     primitive
    0.08
    å¤ļç§įå½¢å¼ı
    0.08
    primitive
    0.08
    Activations Density 0.067%

    No Known Activations