INDEX

Explanations

population

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

 intuit

-0.28

hin

-0.27

abama

-0.27

 tÃ©lÃ©

-0.25

nn

-0.24

anim

-0.24

çĽ¸æľº

-0.24

åģľä¸ĭæĿ¥

-0.24

erals

-0.24

boro

-0.23

POSITIVE LOGITS

source

0.29

ä¸ºä¸ŃåĽ½

0.28

conf

0.27

 Linked

0.26

 source

0.25

onga

0.25

workspace

0.25

 coupled

0.24

 overload

0.24

/workspace

0.24

Activations Density 0.008%

population

No Known Activations