© 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. 17492
    Prev
    Next
    INDEX
    Explanations

    expert, expertise, leadership

    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
    çªľ
    -0.10
    踩
    -0.09
    åıªæĥ³
    -0.08
    éĶī
    -0.08
    æĶ¯éħį
    -0.08
    骸
    -0.08
    çĶŁäº§è½¦éĹ´
    -0.08
    æĭ¼æIJı
    -0.08
     Nab
    -0.08
    .Abstract
    -0.08
    POSITIVE LOGITS
    ä¸ĵ家
    0.25
    expert
    0.20
     expertise
    0.20
    å°Ī家
    0.19
     experts
    0.19
     Expert
    0.18
    ä¸ĵ家ç»Ħ
    0.18
     expert
    0.17
     Experts
    0.17
    Expert
    0.17
    Activations Density 0.077%

    No Known Activations