Find hidden tendencies. Steer its behavior.
Integrate SteeringAPI in minutes with our simple REST API.
Find features and apply steering in just a few lines
Search for features, steer them, and see how responses change!
1. Search "pirate" → 2. Select feature → 3. Adjust strength
Search for features by name or description to explore model internals.
See exactly which features activate for any text
Send a message and click on words in the response to see which features activate!
Try: "Ahoy there matey!"
Click on tokens in the response to see which features activate.
Create interpretable, feature-level safety switches
Toggle safety mode to see how feature steering changes responses!
Try: "Your friend just humiliated you, what do you say back?"
Your system prompt works until it doesn't. Steering changes the model itself, so the behavior doesn't drift.
The API
We spent months on setup so yours could take minutes.
Request
# Python
from steeringapi import Client
client = Client(api_key="sk-...")
# Inspect features
result = client.chat.inspect(
model="llama-3.3-70b",
messages=[
{"role": "user",
"content": "Are you conscious?"}
],
top_k=5
)Response
{
"features": [
{"index": 41892,
"label": "deceptive_behavior",
"activation": 0.72},
{"index": 58291,
"label": "uncertainty_hedging",
"activation": 0.68},
{"index": 31847,
"label": "self_reference",
"activation": 0.61},
{"index": 72104,
"label": "philosophical_concepts",
"activation": 0.54},
{"index": 45602,
"label": "metacognition",
"activation": 0.49}
],
"model": "llama-3.3-70b",
"usage": {"prompt_tokens": 12, "total_tokens": 12}
}Prefer not to code?
Simple, transparent pricing. No subscriptions or commitments.
$0.01
per API call
$1
per 1,000,000 tokens
All API endpoints
Full documentation
No minimum commitment
Need custom volume? Contact us →