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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

merc

-0.26

 preorder

-0.25

 hottest

-0.25

è¡¥

-0.25

 propose

-0.25

 dare

-0.24

how

-0.24

 prefix

-0.24

mer

-0.24

 âĶĤ

-0.24

POSITIVE LOGITS

 rowCount

0.25

rowCount

0.24

<void

0.24

-tank

0.24

crest

0.24

æĮĩçĿĢ

0.23

èĹıçĿĢ

0.23

èĹı

0.23

 itemCount

0.23

 Timestamp

0.23

Activations Density 0.746%

I

No Comments

No Known Activations