© 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. 36241
    Prev
    Next
    INDEX
    Explanations

    expertise

    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
    女士
    -0.10
    å¼ĢæºIJ
    -0.08
    éģ£
    -0.08
    ä¸įåĪĨ
    -0.08
    社ä¼ļåIJĦçķĮ
    -0.08
    å¾Ģäºĭ
    -0.08
    pics
    -0.08
    æ²īéĩį
    -0.08
    computed
    -0.08
     lem
    -0.08
    POSITIVE LOGITS
     expertise
    0.20
    ä¸ĵä¸ļçŁ¥è¯Ĩ
    0.12
     Expert
    0.12
    åĪĩ
    0.12
    expert
    0.12
    ç²¾éĢļ
    0.11
    æľ¬é¢Ĩ
    0.11
    ç²¾æ¹Ľ
    0.10
    çŁ¥èŃĺ
    0.10
    Expert
    0.09
    Activations Density 0.077%

    No Known Activations