INDEX

Explanations

around

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

Accessibility

-0.29

æį£

-0.28

 spread

-0.26

]**

-0.26

emode

-0.26

spread

-0.26

éļĻ

-0.25

.nextInt

-0.25

ivil

-0.24

èĳĽ

-0.24

POSITIVE LOGITS

 transl

0.28

 frontal

0.27

ochen

0.27

 hits

0.27

è¾Ĳ

0.27

ajes

0.26

bur

0.26

hits

0.25

 fron

0.25

alar

0.25

Activations Density 0.012%

around

No Comments

No Known Activations