INDEX

Explanations

cat

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

åľĪ

-0.24

 derivative

-0.24

.componentInstance

-0.24

 plain

-0.24

 Transparent

-0.23

ãĤ³ãĥ³

-0.23

åĽº

-0.23

å¾Ĺå¤ļ

-0.23

å²©

-0.23

 popular

-0.23

POSITIVE LOGITS

çĸĹ

0.28

vation

0.28

BAR

0.28

åĬªåĬĽ

0.27

.attack

0.26

ä»ĸä»¬æĺ¯

0.26

REE

0.26

 thesis

0.25

edImage

0.25

äº²è¿ĳ

0.25

Activations Density 0.006%

cat

No Comments

No Known Activations