INDEX

Explanations

Numbers

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.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

Vo

-0.29

åĪĩ

-0.29

ch

-0.28

cin

-0.26

Vo

-0.26

ä»ĭ

-0.25

chal

-0.25

æ±

-0.25

oods

-0.25

vid

-0.24

POSITIVE LOGITS

lify

0.30

leitung

0.28

elight

0.27

.compress

0.27

)->

0.26

ä¸ĢåĪĻ

0.25

kish

0.25

jang

0.25

edException

0.25

ĳľ

0.24

Activations Density 0.958%

Numbers

No Comments

No Known Activations