© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12295
    Prev
    Next
    INDEX
    Explanations

    successful outcomes

    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
    åıĪè¦ģ
    -0.27
    éĻ¤éĿŀ
    -0.27
    åĪ°æŶåĢĻ
    -0.23
    æľīä¸ĢçĤ¹
    -0.23
    ä¹Łè¦ģ
    -0.23
    æĹ¢è¦ģ
    -0.22
    说ä»Ģä¹Ī
    -0.22
    è¦ģçĶ¨
    -0.22
    åıªæľīä¸Ģ个
    -0.21
    è¦ģèĢĥèĻij
    -0.21
    POSITIVE LOGITS
     successfully
    0.29
    çİĩè¾¾
    0.28
    æĪIJåĬŁ
    0.27
     succès
    0.23
    满æĦı度
    0.23
    åıĸå¾ĹäºĨ
    0.23
     succesfully
    0.23
     successful
    0.22
    æıIJåįĩäºĨ
    0.22
    åĪĨæµģ
    0.22
    Activations Density 0.079%

    No Known Activations