© 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. 13999
    Prev
    Next
    INDEX
    Explanations

    only get

    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
    API
    -0.19
    æľīä»»ä½ķ
    -0.19
    å¸ĥèݱ
    -0.18
    ç²¾è£ħ
    -0.18
     Rede
    -0.18
    å¾Īåĸľæ¬¢
    -0.17
    æľīè¿Ļæł·çļĦ
    -0.17
    è¿Ļ个èģĮä¸ļ
    -0.17
    aggio
    -0.17
    owy
    -0.17
    POSITIVE LOGITS
    ä»ħä»ħæĺ¯
    0.30
    åıªæĺ¯
    0.30
     merely
    0.28
    ä»ħä»ħ
    0.27
     лиÑĪÑĮ
    0.27
    ä»ħ为
    0.25
     simply
    0.24
     mere
    0.24
    ç®ĢåįķçļĦ
    0.24
    ä»ħ
    0.24
    Activations Density 0.209%

    No Known Activations