INDEX

Explanations

-based

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 taps

-0.27

uco

-0.26

_notifier

-0.25

sha

-0.25

 Void

-0.25

 prevalence

-0.25

frequency

-0.24

 foundations

-0.24

org

-0.24

 atop

-0.24

POSITIVE LOGITS

 IonicPage

0.28

leon

0.27

(Unknown

0.26

æĺ¯å¤ļä¹Ī

0.25

.Generated

0.24

?url

0.24

izens

0.24

TRL

0.24

pau

0.24

unicorn

0.23

Activations Density 0.010%

-based

No Comments

No Known Activations