INDEX

Explanations

nerves

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

åİŁ

-0.32

infeld

-0.32

achment

-0.29

Lod

-0.26

åºĶåľ¨

-0.25

 messageType

-0.23

âĻĤ

-0.23

nee

-0.23

åŀĥ

-0.23

bsp

-0.23

POSITIVE LOGITS

 Companion

0.26

member

0.25

 suck

0.25

onen

0.25

éķĶ

0.25

 nameof

0.24

ãĥĭãĥ³ãĤ°

0.24

paced

0.23

 idle

0.23

åĨµ

0.23

Activations Density 0.001%

nerves

No Comments

No Known Activations