INDEX

Explanations

ace

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

Sent

-0.27

 growing

-0.26

 expanding

-0.26

 proposition

-0.25

éĻĢ

-0.25

åĳĺå·¥

-0.25

 Sent

-0.24

Rol

-0.24

IRR

-0.24

ä¸įåİ»

-0.24

POSITIVE LOGITS

 PARTICULAR

0.28

issan

0.26

aversal

0.26

umn

0.25

çīĮåŃĲ

0.25

STALL

0.25

Ð¶Ð´

0.25

XObject

0.24

-publish

0.24

ifact

0.24

Activations Density 0.476%

ace

No Comments

No Known Activations