INDEX

Explanations

of

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

–

-0.29

RTOS

-0.28

 roles

-0.27

RESP

-0.26

_roles

-0.26

 coded

-0.25

osite

-0.25

 instruct

-0.25

 trickle

-0.25

ooks

-0.25

POSITIVE LOGITS

eren

0.27

Parking

0.26

éħĨ

0.25

 Komment

0.24

abcdefghijklmnop

0.24

 Employ

0.24

éªĳå£«

0.24

enberg

0.24

%=

0.24

cala

0.23

Activations Density 0.001%

of

No Comments

No Known Activations