INDEX

Explanations

B

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

ped

-0.30

pedia

-0.27

idunt

-0.27

éĺŁä¼įå»ºè®¾

-0.27

æĺ¯åĲ¦æľī

-0.25

å¡ĺ

-0.24

å°±åı¯ä»¥äºĨ

-0.24

ä¸Ģæ¬¾

-0.24

articles

-0.24

 experienced

-0.23

POSITIVE LOGITS

 orally

0.29

 blindly

0.27

 innoc

0.27

 Powers

0.25

 Norris

0.25

IRQ

0.24

.metric

0.24

åİĺ

0.24

 Dreams

0.24

æĸ°é²ľ

0.24

Activations Density 0.004%

B

No Comments

No Known Activations