INDEX

Explanations

i

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-pocket

-0.28

iÃ«

-0.27

ivar

-0.26

Ã¸j

-0.26

åı£è¢ĭ

-0.25

éĸ±

-0.25

ItemAt

-0.25

 indian

-0.25

éĵĳ

-0.24

Ð¾Ð»ÑĮÐ·Ð¾Ð²

-0.24

POSITIVE LOGITS

.cloudflare

0.29

uffman

0.28

sign

0.27

andel

0.27

Signing

0.27

.sign

0.26

ute

0.25

mant

0.25

 mutate

0.25

/sign

0.25

Activations Density 0.041%

i

No Comments

No Known Activations