INDEX

Explanations

area measurements

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

éľľ

-0.34

arked

-0.33

elm

-0.32

åĲİæİĴ

-0.27

ellow

-0.27

Ø³Ø§Ø³

-0.26

laden

-0.26

 escalation

-0.25

éĩĩæļĸ

-0.25

ä¾¿äºİ

-0.25

POSITIVE LOGITS

å¼±çĤ¹

0.27

å¹´äº§åĢ¼

0.26

WithData

0.26

Äįe

0.26

 pronounce

0.26

orarily

0.25

æ°´æºĲ

0.25

ographers

0.25

æĢ»äº§åĢ¼

0.25

 granddaughter

0.25

Activations Density 0.001%

area measurements

No Comments

No Known Activations