INDEX

Explanations

environment

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

æ·±äº¤

-0.27

éĿĴå±±

-0.27

æĮ£éĴ±

-0.26

leo

-0.26

æ±Ĭ

-0.26

(begin

-0.26

lotte

-0.25

ABB

-0.25

 virtue

-0.25

ebb

-0.24

POSITIVE LOGITS

 flight

0.27

 Blank

0.26

lab

0.26

 Labels

0.25

ç©¹

0.24

ĳľ

0.24

Suit

0.24

Ø¬Ø§Ø±

0.24

æĮĩå¯¼ä¸ĭ

0.24

dem

0.24

Activations Density 0.007%

environment

No Comments

No Known Activations