INDEX

Explanations

hex

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

TA

-0.33

RAY

-0.29

/loader

-0.28

ray

-0.28

tap

-0.27

å¼¹

-0.27

Ta

-0.25

Digits

-0.25

CLU

-0.25

tap

-0.24

POSITIVE LOGITS

rets

0.27

gÃ©

0.25

ÃŃst

0.25

.setGeometry

0.24

 retirement

0.24

~~~~~~~~

0.24

centers

0.24

ivated

0.24

ħ§

0.24

enko

0.23

Activations Density 0.024%

hex

No Comments

No Known Activations