INDEX

Explanations

Michigan

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_20.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.20.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

aign

-0.29

åĽ±

-0.28

µľ

-0.27

Crow

-0.27

ighet

-0.25

 sooner

-0.25

olut

-0.25

 tweeting

-0.24

ght

-0.24

agra

-0.24

POSITIVE LOGITS

$$$$

0.26

èįĨ

0.26

èį

0.26

æĭŁ

0.25

MOST

0.25

æī¬

0.24

ODY

0.24

 cores

0.24

[src

0.24

çĿģ

0.24

Activations Density 2.951%

Michigan

No Known Activations