INDEX

Explanations

infant

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ute

-0.31

rand

-0.29

 rand

-0.28

UDA

-0.27

æĮĳæĪĺ

-0.25

pts

-0.25

rnd

-0.25

 Cham

-0.25

mdat

-0.25

æĴŀåĩ»

-0.25

POSITIVE LOGITS

éĢŀ

0.27

riba

0.27

æħİéĩį

0.26

ouncill

0.26

 wczeÅĽniej

0.25

æĽ©

0.25

å¶Ļ

0.24

 nominees

0.24

ibre

0.24

ä½¼

0.23

Activations Density 0.028%

infant

No Comments

No Known Activations