INDEX

Explanations

rare tokens

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_33.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.33.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

-0.34

iv

-0.32

_block

-0.30

,i

-0.29

(i

-0.28

ç§ĳ

-0.28

æ²»

-0.28

tÃ©

-0.28

iii

-0.28

 Block

-0.27

POSITIVE LOGITS

strup

0.31

è§īå¾Ĺå¾Ī

0.28

cud

0.28

èĪ¯

0.27

Ð°ÑĤÐµÐ»ÑĮ

0.26

å¸

0.26

naire

0.26

æĦŁåĪ°

0.25

.setTo

0.25

(getString

0.25

Activations Density 0.005%

rare tokens

No Known Activations