INDEX

Explanations

ody

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

razy

-0.29

esan

-0.29

çºłéĶĻ

-0.28

quit

-0.26

mods

-0.26

libs

-0.25

æĭĺ

-0.25

orious

-0.25

pÃ©ri

-0.25

pole

-0.25

POSITIVE LOGITS

Ki

0.30

æĪĲå¹´äºº

0.27

 individual

0.25

Ki

0.24

beck

0.24

ç¦ı

0.24

 ?↵↵

0.24

itet

0.24

 blocking

0.23

è¤

0.23

Activations Density 0.001%

ody

No Comments

No Known Activations