INDEX

Explanations

a/an

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

 captive

-0.29

 otherwise

-0.26

asing

-0.26

Otherwise

-0.25

ä¼ĳ

-0.25

\Mapping

-0.24

åľĨå½¢

-0.23

otherwise

-0.23

 convicted

-0.23

 Halloween

-0.23

POSITIVE LOGITS

HEN

0.30

ament

0.29

hen

0.28

redni

0.28

mens

0.28

elman

0.26

ĵį

0.26

NER

0.25

ERO

0.25

(scan

0.25

Activations Density 0.002%

a/an

No Comments

No Known Activations