INDEX

Explanations

degree or quality

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

$($

-0.27

bi

-0.27

 Rowe

-0.26

ieu

-0.26

ä¸»

-0.25

 offensive

-0.25

éĻĽ

-0.25

Ð±Ð¸

-0.24

æĶ¹

-0.24

adden

-0.24

POSITIVE LOGITS

opsis

0.27

ymbol

0.27

ampa

0.24

.AddComponent

0.24

\Helpers

0.24

WithMany

0.24

gradient

0.23

javascript

0.23

opsy

0.23

jej

0.23

Activations Density 0.002%

degree or quality

No Comments

No Known Activations