INDEX

Explanations

written

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

éĻĤ

-0.29

DER

-0.28

-share

-0.28

adera

-0.28

åĲĳçĿĢ

-0.27

 Trucks

-0.27

WRITE

-0.27

der

-0.27

isans

-0.26

ä¹ĹãĤĬ

-0.26

POSITIVE LOGITS

çĨ¹

0.28

utely

0.27

olog

0.26

æłĩå¿Ĺ

0.25

itone

0.25

ear

0.24

lvl

0.24

oud

0.24

Band

0.24

contr

0.24

Activations Density 0.010%

written

No Comments

No Known Activations