INDEX

Explanations

take

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

gar

-0.28

io

-0.27

server

-0.26

gly

-0.26

formats

-0.25

success

-0.25

aring

-0.24

ga

-0.23

arta

-0.23

itary

-0.23

POSITIVE LOGITS

çļĦåħ³æ³¨

0.31

éĩįçĤ¹åħ³æ³¨

0.28

storybook

0.26

Ĭ¶

0.25

 Hoff

0.25

inn

0.24

WN

0.24

uspendLayout

0.24

[]{

0.24

bum

0.23

Activations Density 0.016%

take

No Comments

No Known Activations