INDEX

Explanations

Academic texts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ansion

-0.31

THR

-0.29

 theirs

-0.27

èĲ¥

-0.26

æ°¸ä¹ħ

-0.25

Season

-0.25

 hers

-0.25

åŃ£èĬĤ

-0.25

otti

-0.24

éĢĤåĲĪ

-0.24

POSITIVE LOGITS

 compound

0.32

åĮ¡

0.29

 Compound

0.28

compound

0.27

setEnabled

0.25

å®ŀäºĭæ±Ĥæĺ¯

0.25

.setFocus

0.24

Compound

0.24

åŃ¦çĶŁä»¬

0.24

è°Į

0.24

Activations Density 0.001%

Academic texts

No Comments

No Known Activations