krnel-ai/krnel-graph
Lightweight representation engineering dataflow operations for agent developers.
This is a Python toolbox for researchers focused on understanding how large language models (LLMs) work internally. It helps you feed text data into an LLM, extract the internal patterns (activations) the model generates, and then use those patterns to train other small models (linear probes) to analyze specific model behaviors like safety or bias. This tool is for AI researchers, particularly those in mechanistic interpretability.
Use this if you are a researcher trying to understand the inner workings of large language models by extracting and analyzing their internal representations.
Not ideal if you are looking for a tool to simply deploy or fine-tune existing language models for general applications without deep internal analysis.
Stars
22
Forks
1
Language
Python
License
Apache-2.0
Category
Last pushed
Feb 23, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/krnel-ai/krnel-graph"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
SamsungSAILMontreal/nino
Code for "Accelerating Training with Neuron Interaction and Nowcasting Networks" [ICLR 2025]
graphdeeplearning/graphtransformer
Graph Transformer Architecture. Source code for "A Generalization of Transformer Networks to...
vijaydwivedi75/gnn-lspe
Source code for GNN-LSPE (Graph Neural Networks with Learnable Structural and Positional...
snap-stanford/relgt
Relational Graph Transformer
omron-sinicx/crystalframer
The official code respository for "Rethinking the role of frames for SE(3)-invariant crystal...