INDEX

Explanations

declar

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

.blog

-0.27

_operator

-0.27

/operators

-0.26

emploi

-0.24

æľĿéĺ³

-0.24

shaw

-0.24

 Thrones

-0.24

çľĭå®Į

-0.24

bler

-0.23

åĨ²åĬ¨

-0.23

POSITIVE LOGITS

enet

0.28

coat

0.27

{.

0.27

xde

0.26

èĿ¾

0.25

ä¼ł

0.25

oll

0.25

ëĭ¥

0.25

çħ

0.25

lit

0.24

Activations Density 0.006%

declar

No Comments

No Known Activations