© 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. 13017
    Prev
    Next
    INDEX
    Explanations

    donation or fee

    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
    æ»Ķ
    -0.21
    è½
    -0.21
    æĪĺçķ¥å¸ĥå±Ģ
    -0.20
    åķĨæłĩ
    -0.20
    çľĭæĿ¥
    -0.19
    åīĶ
    -0.19
    ä¸įçŁ¥
    -0.19
    笼
    -0.19
    favicon
    -0.19
    楼
    -0.19
    POSITIVE LOGITS
     donation
    0.22
     Ware
    0.21
     sliding
    0.21
     slips
    0.21
     Slip
    0.21
     conscience
    0.21
     Wilde
    0.20
    ware
    0.20
     slip
    0.19
    nom
    0.19
    Activations Density 0.008%

    No Known Activations