INDEX

Explanations

health

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

zip

-0.30

_wr

-0.29

Wr

-0.28

zip

-0.28

(zip

-0.27

 wrap

-0.27

 Wrap

-0.27

Wr

-0.27

.zip

-0.26

_WR

-0.26

POSITIVE LOGITS

elves

0.33

ponents

0.28

 undercover

0.25

elled

0.25

åľ°éģĵ

0.25

å²ģä»¥ä¸Ĭ

0.25

æµ·ç»µ

0.25

è¾Ł

0.24

elf

0.24

noÅĽÄĩ

0.24

Activations Density 0.010%

health

No Comments

No Known Activations