INDEX

Explanations

1

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

Ħä»¶

-0.34

 Ã¡n

-0.27

oplast

-0.27

åĪŃ

-0.26

addtogroup

-0.23

ÃŃv

-0.23

ALLY

-0.23

èıĤ

-0.23

‘

-0.23

POSITIVE LOGITS

ç¿ĺ

0.28

cko

0.28

lover

0.27

æ¢ħ

0.27

crm

0.26

elow

0.25

stances

0.25

heiten

0.24

gren

0.24

tre

0.24

Activations Density 0.079%

1

No Comments

No Known Activations