INDEX

Explanations

phone

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

 Brigham

-0.28

.console

-0.26

Converted

-0.26

 Converted

-0.25

ãĤĥ

-0.25

hton

-0.25

ponsored

-0.25

çĽħ

-0.25

æİĴè¡Į

-0.24

èĴ¸

-0.24

POSITIVE LOGITS

apel

0.27

 nearest

0.26

ritz

0.25

 Ð°Ð¿Ð¿Ð°ÑĢÐ°ÑĤ

0.25

 Dark

0.24

 provoc

0.24

ç¦ģå¿Į

0.24

Principal

0.23

å¾®

0.23

ceptar

0.23

Activations Density 0.049%

phone

No Comments

No Known Activations