INDEX

Explanations

code excerpts

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.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

uhan

-0.28

çīĩéĿ¢

-0.28

aha

-0.26

ihan

-0.25

èł¹

-0.25

 Conor

-0.24

½Ķ

-0.24

icable

-0.24

oogle

-0.23

¶Ī

-0.23

POSITIVE LOGITS

alem

0.27

chal

0.27

fav

0.27

çĶ¨éĢĶ

0.26

 sÄ±k

0.25

ÄĿ

0.25

ObjectContext

0.25

mue

0.24

Lov

0.24

 []).

0.24

Activations Density 0.000%

code excerpts

No Comments

No Known Activations