Neural Transparency: Mechanistic Interpretability Interfaces for Anticipating Model Behaviors for Personalized AI
October 31, 2025 Β· Declared Dead Β· π arXiv.org
"No code URL or promise found in abstract"
Evidence collected by the PWNC Scanner
Authors
Sheer Karny, Anthony Baez, Pat Pataranutaporn
arXiv ID
2511.00230
Category
cs.HC: Human-Computer Interaction
Cross-listed
cs.AI
Citations
0
Venue
arXiv.org
Last Checked
4 months ago
Abstract
Millions of users now design personalized LLM-based chatbots that shape their daily interactions, yet they can only roughly anticipate how their design choices will manifest as behaviors in deployment. This opacity is consequential: seemingly innocuous prompts can trigger excessive sycophancy, toxicity, or other undesirable traits, degrading utility and raising safety concerns. To address this issue, we introduce an interface that enables neural transparency by exposing language model internals during chatbot design. Our approach extracts behavioral trait vectors (empathy, toxicity, sycophancy, etc.) by computing differences in neural activations between contrastive system prompts that elicit opposing behaviors. We predict chatbot behaviors by projecting the system prompt's final token activations onto these trait vectors, normalizing for cross-trait comparability, and visualizing results via an interactive sunburst diagram. To evaluate this approach, we conducted an online user study using Prolific to compare our neural transparency interface against a baseline chatbot interface without any form of transparency. Our analyses suggest that users systematically miscalibrated AI behavior: participants misjudged trait activations for eleven of fifteen analyzable traits, motivating the need for transparency tools in everyday human-AI interaction. While our interface did not change design iteration patterns, it significantly increased user trust and was enthusiastically received. Qualitative analysis revealed nuanced user experiences with the visualization, suggesting interface and interaction improvements for future work. This work offers a path for how mechanistic interpretability can be operationalized for non-technical users, establishing a foundation for safer, more aligned human-AI interactions.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
π Similar Papers
In the same crypt β Human-Computer Interaction
R.I.P.
π»
Ghosted
R.I.P.
π»
Ghosted
Improving fairness in machine learning systems: What do industry practitioners need?
R.I.P.
π»
Ghosted
Identifying Stable Patterns over Time for Emotion Recognition from EEG
R.I.P.
π»
Ghosted
Questioning the AI: Informing Design Practices for Explainable AI User Experiences
R.I.P.
π»
Ghosted
Deep Learning for Sensor-based Human Activity Recognition: Overview, Challenges and Opportunities
R.I.P.
π»
Ghosted
Educational data mining and learning analytics: An updated survey
Died the same way β π» Ghosted
R.I.P.
π»
Ghosted
Federated Learning: Strategies for Improving Communication Efficiency
R.I.P.
π»
Ghosted
In-Datacenter Performance Analysis of a Tensor Processing Unit
R.I.P.
π»
Ghosted
Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning
R.I.P.
π»
Ghosted