INDEX

Explanations

2

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

eff

-0.29

eff

-0.29

_eff

-0.28

noon

-0.27

ffffffff

-0.26

çĬ¶

-0.26

WAR

-0.25

Eff

-0.25

istik

-0.24

 mode

-0.24

POSITIVE LOGITS

åĪģ

0.29

 Glide

0.28

headers

0.27

inha

0.25

å¹²åĩĢ

0.24

atak

0.24

å¼Ģåĩº

0.24

=headers

0.24

.registration

0.24

åı¤

0.24

Activations Density 0.220%

2

No Comments

No Known Activations