INDEX

Explanations

fixed

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

 production

-0.28

ä½ŀ

-0.27

elix

-0.27

houses

-0.26

ä¸ĢåĪĩ

-0.26

 houses

-0.26

 mill

-0.26

lay

-0.25

qb

-0.25

fil

-0.25

POSITIVE LOGITS

_tac

0.28

hta

0.27

èıĸ

0.25

tok

0.24

pees

0.24

æĬķèµĦé¡¹çĽ®

0.24

æĪı

0.24

åĪĨå¸ĥ

0.24

tob

0.24

 demands

0.23

Activations Density 0.862%

fixed

No Comments

No Known Activations