INDEX

Explanations

code/technical language

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

å¤©èĬ±

-0.27

.orientation

-0.26

ichi

-0.25

 banker

-0.25

Segment

-0.24

SSI

-0.24

éĥ¨

-0.24

fections

-0.24

_epi

-0.24

riot

-0.23

POSITIVE LOGITS

ame

0.29

 serv

0.27

 trailed

0.27

atin

0.26

åĲİæĤĶ

0.25

 buurt

0.25

 hung

0.25

åģľçĶµ

0.24

rone

0.24

æ³ķåħ°

0.24

Activations Density 0.929%

code/technical language

No Comments

No Known Activations