© 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. 10983
    Prev
    Next
    INDEX
    Explanations

    numbers in sql or json context

    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
    sic
    -0.19
     ChÃŃ
    -0.19
    æĶ¹æŃ£
    -0.18
     manic
    -0.18
     c
    -0.18
    对ä»ĸ们
    -0.18
    æīİ
    -0.18
     recal
    -0.17
     these
    -0.17
     xu
    -0.17
    POSITIVE LOGITS
    æŀ°
    0.22
    iped
    0.20
    unner
    0.20
    ounder
    0.20
     Seeder
    0.20
    åIJĥè¿ĩ
    0.19
    èĹľ
    0.19
    æĬĦè¢Ń
    0.19
    кÑĤ
    0.19
    æ£Ģçĸ«
    0.18
    Activations Density 0.166%

    No Known Activations