© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12644
    Prev
    Next
    INDEX
    Explanations

    cerebral insufficiency, neurodegenerative disorders

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    gue
    -0.22
     Automation
    -0.20
    åIJĪéĢĤ
    -0.20
    CSR
    -0.20
    gu
    -0.19
    Automation
    -0.19
    .Automation
    -0.19
    è¡İ
    -0.18
    èĩªåĬ¨åĮĸ
    -0.18
    cot
    -0.18
    POSITIVE LOGITS
    ä¼ĺåĮĸ
    0.33
    åĬłéĢŁ
    0.28
    æĶ¹åĸĦ
    0.26
     optimizer
    0.25
     purported
    0.24
    å¢ŀ强
    0.23
    æķĪæŀľ
    0.22
     optimize
    0.22
    禹
    0.21
     phantom
    0.21
    Activations Density 0.185%

    No Known Activations