Skip to content
nnsight
tracing
Initializing search
ndif-team/nnsight
Home
Getting Started
Documentation
Features
vLLM
Tutorials
Blog
Status
About
nnsight
ndif-team/nnsight
Home
Getting Started
Getting Started
Installation
Quick Start
Documentation
Documentation
_c
_c
backtrace
intervention
intervention
backends
backends
display
local
remote
backward
barrier
batching
cache
editing
envoy
eproperty
errors
fragments
interleaver
iterator
serialization
source
tracer
util
modeling
modeling
base
diffusion
huggingface
language
mixins
mixins
loadable
meta
remotable
quantization
tp
tp
envoys
fragments
plan
transformers
vllm
vllm
async_backend
batching
collect
envoys
engines
engines
engine
fragments
interleaver
model_runners
model_runners
GPUModelRunner
registration
serve
serve
backend
cli
http
server
tracer
vllm
workers
workers
GPUWorker
vlm
schema
schema
config
request
response
tracing
tracing
backend
globals
hint
tracer
util
ndif
util
Features
Features
Getting Activations
Setting Activations
Gradients
Multiple Token Generation
Loading a Model
Module Access
Model Editing
Batching
Empty Invokers
Cache
Intermediate Operations
Early Stopping
Skip Execution
Scan
Remote Execution
vLLM
Tensor Parallelism
Quantization
vLLM
vLLM
Locations
Models
Models
Loading models
Capabilities and limits
Reading
Reading
Capture
Attention
Logit lens
Writing
Writing
Steering
Activation patching
Ablation
Direct logit attribution
Conditional interventions
SAE features
Editing the engine
Generating
Generating
Generation
Chat and tokens
Serving
Serving
Async and servers
Tensor parallelism
Examples
Examples
Causal tracing
Jacobian lens
A linear probe
Concept directions
Performance
Comparisons
Tutorials
Tutorials
Tutorials
Tutorials
Getting Started
Getting Started
Walkthrough
Chat Templates
Remote Access
Migrating
Migrating
From TransformerLens
Causal Tracing
Causal Tracing
Causal Models Intro
Activation Patching
Attribution Patching
Causal Mediation I
Causal Mediation II
DAS
Probing
Probing
Logit Lens
Diffusion Lens
Concept Erasure
Attention
Attention
Attention Patterns and Per-Head Detection
Circuits
Circuits
Attribution Graphs
Architectures
Architectures
MoE Routing
State-Space Models
Engineering
Engineering
Dataset-Scale Activation Caching
Steering
Steering
Dictionary Learning
Evaluating SAEs
LoRA Tutorial
Vision
Vision
Cross-Attention Ablation
Mini Papers
Mini Papers
Function Vectors
Massive Activations
Induction Heads and the ICL Phase Change
Under-trained Tokens
Chain-of-Thought Faithfulness
Belief Lookbacks
Geometry of Truth
LLM Depth
Dual Route Induction
Demystifying Memorization
Jacobian Lens
Patchscopes
IOI Path Patching
Progress Measures for Grokking
Emergent World Models
Concept Attention
VLM Logit Lens
Cyclic Arithmetic
Gaze Heads
Blog
Blog
Archive
Archive
2026
Categories
Categories
Ecosystem
Guide
Release
Status
About
About
Table of contents
tracing
Submodules
tracing
¶
tracing
¶
Submodules
¶
backend
globals
hint
tracer
util
Back to top