INDEX

Explanations

sentinel or risky tests

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Hierarchy

-0.29

avoid

-0.27

Twe

-0.25

éģ¿åħį

-0.25

hpp

-0.24

estre

-0.24

sequential

-0.24

izz

-0.24

 hier

-0.24

 THEORY

-0.24

POSITIVE LOGITS

æİ¢

0.27

erman

0.26

éº»

0.25

 Leading

0.25

 leading

0.24

è®¡åĪĴçĶŁèĤ²

0.24

 Modal

0.24

æ±²

0.23

å¼ĢéĹ¨

0.23

.dev

0.23

Activations Density 0.003%

sentinel or risky tests

No Comments

No Known Activations