INDEX

Explanations

words related to saying

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

umat

-0.28

zier

-0.27

CIT

-0.26

çĿĢä»ĸ

-0.24

 Nikol

-0.24

kinson

-0.24

ä¸ĢéĿ¢

-0.23

 compat

-0.23

å®¡æī¹

-0.23

åĬ©æīĭ

-0.23

POSITIVE LOGITS

ahi

0.28

/(

0.27

é£İåĲ¹

0.27

ores

0.27

ORE

0.27

oref

0.26

áºŃy

0.25

endor

0.25

 Press

0.25

è³ª

0.25

Activations Density 0.001%

words related to saying

No Comments

No Known Activations