INDEX

Explanations

code snippets

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ull

-0.26

 Bull

-0.25

kop

-0.25

Ð±Ð¸ÑĤ

-0.25

 tele

-0.24

kit

-0.24

bull

-0.24

 differently

-0.24

itles

-0.24

tele

-0.23

POSITIVE LOGITS

ä¾Ľ

0.26

dden

0.26

èį·

0.25

 Revolutionary

0.24

æķ²

0.24

çĮ«

0.24

Ä±n

0.23

å©º

0.23

-loading

0.23

æµĳ

0.23

Activations Density 0.002%

code snippets

No Comments

No Known Activations