Scholar
Julian Minder
Google Scholar ID: mu1tLSoAAAAJ
EPFL/ETHZ
Mechanistic Interpretability
NLP
Graph Learning
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
66
H-index
4
i10-index
3
Publications
8
Co-authors
23
list available
Publications
8 items
Diff Mining: Logit Differences Reveal Finetuning Objectives
2026
Cited
0
Synthetic Persona Pretraining: Alignment from Token Zero
2026
Cited
0
Activation Oracles: Training and Evaluating LLMs as General-Purpose Activation Explainers
2025
Cited
0
Believe It or Not: How Deeply do LLMs Believe Implanted Facts?
2025
Cited
0
Narrow Finetuning Leaves Clearly Readable Traces in Activation Differences
2025
Cited
0
The Non-Linear Representation Dilemma: Is Causal Abstraction Enough for Mechanistic Interpretability?
2025
Cited
0
Robustly identifying concepts introduced during chat fine-tuning using crosscoders
2025
Cited
0
Controllable Context Sensitivity and the Knob Behind It
arXiv.org · 2024
Cited
0
Co-authors
16 total
Neel Nanda
Mechanistic Interpretability Team Lead, Google DeepMind
Clément Dumas
ENS Paris-Saclay
Katya Mirylenka
Zalando Switzerland
Bilal Chughtai
Google DeepMind
Niklas Stoehr
Google DeepMind, ETH Zurich
Chris Wendler
Northeastern University
Ryan Cotterell
ETH Zürich
Giovanni Monea
Cornell University
