INDEX

Explanations

8

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_2.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.2.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

aver

-0.28

å¼Ģè¾Ł

-0.27

(sensor

-0.27

**

-0.26

hiro

-0.25

è¦ģåİ»

-0.25

eeper

-0.24

 exchanging

-0.24

èį»

-0.24

 depths

-0.23

POSITIVE LOGITS

.tie

0.28

éłģ

0.26

 è¯·æ±Ĥ

0.26

å¦ª

0.25

 /↵↵

0.25

ContentPane

0.25

ä¸ĩè¾Ĩ

0.25

axed

0.24

 grosse

0.24

è¯·æ±Ĥ

0.24

Activations Density 52.473%

8

No Comments

No Known Activations