© 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. 554
    Prev
    Next
    INDEX
    Explanations

    medical specialties and conditions

    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
    irma
    -0.24
    åħ¶ä¸Ńæľī
    -0.23
     unlucky
    -0.23
    绫
    -0.22
    getModel
    -0.22
    oras
    -0.22
    æĪijçİ°åľ¨
    -0.21
     freshly
    -0.21
    vin
    -0.21
    eners
    -0.21
    POSITIVE LOGITS
    -wide
    0.39
    -specific
    0.39
    æĸ¹éĿ¢çļĦ
    0.32
    -related
    0.31
    ä¸ĵå±ŀ
    0.31
    -wise
    0.29
    -centric
    0.29
    -to
    0.27
    -themed
    0.27
    -side
    0.26
    Activations Density 0.858%

    No Known Activations