INDEX

Explanations

at

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

 launches

-0.28

.maps

-0.25

—from

-0.25

PCs

-0.25

æ··

-0.25

 Äĳá»©c

-0.25

è·Ŀ

-0.25

arLayout

-0.24

èļ¬

-0.24

 launching

-0.24

POSITIVE LOGITS

rin

0.29

SKI

0.26

æĿ²

0.25

oled

0.25

çłĶç©¶çĶŁ

0.25

Scientists

0.25

ogue

0.25

/of

0.25

zb

0.24

edics

0.24

Activations Density 0.017%

at

No Comments

No Known Activations