INDEX

Explanations

this

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_22.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.22.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

ene

-0.30

ä¸Ŀ

-0.28

ENE

-0.27

BE

-0.27

åķ¼

-0.27

èĭĽ

-0.26

 incident

-0.25

leÅŁ

-0.25

 benches

-0.25

logfile

-0.25

POSITIVE LOGITS

ieval

0.31

.retrieve

0.26

 Laser

0.26

åĢ¼å¾Ĺä¸Ģ

0.25

intent

0.25

reative

0.25

osg

0.24

çĽ¼

0.24

wag

0.24

è¿ĩå¾Ĺ

0.24

Activations Density 0.075%

this

No Known Activations