INDEX

Explanations

story

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_9.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.9.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

ä¸įåĲĪ

-0.29

Saved

-0.29

orm

-0.26

ORN

-0.26

.pref

-0.26

 borderTop

-0.26

äº¤æį¢

-0.25

 saved

-0.25

 Prefix

-0.25

Dia

-0.25

POSITIVE LOGITS

æĸĩä¹¦

0.31

 KING

0.29

èĬĹ

0.27

 krat

0.26

ìĺģìĥģ

0.25

ano

0.24

vez

0.24

 King

0.24

Ãºt

0.24

ves

0.24

Activations Density 0.480%

story

No Known Activations