© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 414
    Prev
    Next
    INDEX
    Explanations

    pharmaceutical industry and companies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    alue
    -0.26
    ted
    -0.23
    rophe
    -0.23
    éĬ®
    -0.23
     clinically
    -0.23
    书记
    -0.22
    htag
    -0.22
     sonic
    -0.22
    Disposition
    -0.22
     hearing
    -0.21
    POSITIVE LOGITS
    巨头
    0.38
    åħ¬åı¸çļĦ
    0.36
     companies
    0.32
    æĢ»åħ¬åı¸
    0.31
     company
    0.31
    åħ¬åı¸åľ¨
    0.30
     giants
    0.30
    åħ¬åı¸å°Ĩ
    0.30
    åħ¬åı¸
    0.30
    ä¼ģä¸ļåĴĮ
    0.30
    Activations Density 0.012%

    No Known Activations