INDEX

Explanations

scientific/technical writing

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_9.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.9.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rette

-0.27

RET

-0.26

_ret

-0.25

èĥ½å¾ĹåĪ°

-0.25

_INITIALIZER

-0.25

èĿ¥

-0.24

ç»Ļä»ĸä»¬

-0.24

åīįä»»

-0.24

olders

-0.24

>{!!

-0.24

POSITIVE LOGITS

hog

0.28

éĢļ

0.28

.HttpServlet

0.27

-backed

0.26

tg

0.25

å°±æľīäºĨ

0.25

tg

0.25

Only

0.24

 knocking

0.24

ÃŃc

0.24

Activations Density 1.235%

scientific/technical writing

No Comments

No Known Activations