INDEX

Explanations

Impro

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.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

[](

-0.26

 controlled

-0.26

	ctrl

-0.25

 elic

-0.25

Fig

-0.25

.dump

-0.24

wright

-0.24

ä¸»

-0.24

èĲ§

-0.23

ç§°ä¹ĭ

-0.23

POSITIVE LOGITS

æ¬¢

0.26

anni

0.26

å®Ļ

0.25

Ø§Ø¹

0.25

QUEUE

0.25

åŀĽ

0.25

ponsor

0.24

REPORT

0.24

éĩįè¦ģæĦıä¹ī

0.24

ÙĩØ¨

0.24

Activations Density 0.054%

Impro

No Comments

No Known Activations