INDEX

Explanations

"to be" verbs

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

hol

-0.27

 halo

-0.27

åİ»ä¹°

-0.26

OLA

-0.26

æĦļ

-0.25

OL

-0.25

vt

-0.25

å»ºè®¾åĴĮ

-0.25

å»īæĶ¿

-0.25

ÑĪÐºÐ°

-0.24

POSITIVE LOGITS

 phased

0.28

natural

0.25

 natural

0.25

getSession

0.25

_pll

0.24

 sess

0.24

æĿ¾

0.24

rophy

0.24

 relying

0.23

cona

0.23

Activations Density 0.260%

"to be" verbs

No Comments

No Known Activations