© 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. 10814
    Prev
    Next
    INDEX
    Explanations

    American Recovery and Reinvestment Act

    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
    æĵį
    -0.20
     cum
    -0.19
    caps
    -0.18
    llib
    -0.18
    ä¸ĢæĬĬ
    -0.18
    изма
    -0.18
     Graves
    -0.17
    æİ¥è¿ĩ
    -0.17
    åĪ³
    -0.17
    åĬ¾
    -0.17
    POSITIVE LOGITS
    è´´
    0.21
    ensis
    0.21
    è²¼
    0.21
    便
    0.20
     Nap
    0.20
    Memo
    0.19
    大约
    0.19
    éĶ¦ç»£
    0.19
    ç¥Ī
    0.18
    bose
    0.18
    Activations Density 0.001%

    No Known Activations