INDEX

Explanations

used

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.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

å°Ķ

-0.27

èª

-0.25

å¦¨

-0.24

çĤ¹èµŀ

-0.23

unm

-0.23

 Orientation

-0.23

 Composer

-0.23

 láº½

-0.23

 Ã©v

-0.23

 getDescription

-0.23

POSITIVE LOGITS

utility

0.30

in

0.28

 later

0.27

 util

0.27

rame

0.27

chers

0.27

for

0.26

fold

0.26

 campaigned

0.25

Ren

0.25

Activations Density 0.014%

used

No Comments

No Known Activations