INDEX

Explanations

is

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

oc

-0.31

oc

-0.27

parent

-0.26

pack

-0.26

rus

-0.26

Comp

-0.26

aling

-0.25

illusion

-0.25

cap

-0.25

.sm

-0.25

POSITIVE LOGITS

éĢŀ

0.30

cta

0.26

-peer

0.26

 crackers

0.25

entially

0.25

URING

0.25

Ð¾Ñī

0.25

icha

0.25

æģŃåĸľ

0.25

SOFTWARE

0.24

Activations Density 0.000%

is

No Comments

No Known Activations