© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 14411
    Prev
    Next
    INDEX
    Explanations

    company names ending in Corporation or Co

    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
    çĵľ
    -0.24
    å¼ij
    -0.22
    datatable
    -0.21
    raid
    -0.20
    REGISTER
    -0.20
    æ¶ĤæĬ¹
    -0.19
    åįıä¼ļä¼ļåijĺ
    -0.19
    çĤķ
    -0.19
    eko
    -0.18
     bra
    -0.18
    POSITIVE LOGITS
    æķ´ä½ĵ
    0.26
     анг
    0.21
    çļĦæķ´ä½ĵ
    0.20
    .utilities
    0.19
    warts
    0.19
    æĸ¤
    0.18
    主å¸Ń
    0.18
     predecessor
    0.18
     Components
    0.18
    .argv
    0.18
    Activations Density 0.061%

    No Known Activations