INDEX

Explanations

miniaturization substring

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 acad

-0.27

PTS

-0.27

gren

-0.26

è§ŀ

-0.25

uyo

-0.25

 Dund

-0.24

ixe

-0.23

'Neill

-0.23

CppType

-0.23

Ã©rt

-0.23

POSITIVE LOGITS

Chip

0.27

 sometimes

0.27

 Chip

0.27

bare

0.26

ATED

0.25

è¹Ħ

0.25

å¤¥

0.25

 Compound

0.25

 barring

0.25

less

0.24

Activations Density 0.004%

miniaturization substring

No Comments

No Known Activations