INDEX

Explanations

and

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

Not in Any Lists

No Comments

Negative Logits

aho

-0.29

å¢Ģ

-0.28

vic

-0.26

resco

-0.25

 pedest

-0.25

keeping

-0.25

åĨ²

-0.25

ally

-0.24

ress

-0.24

PET

-0.24

POSITIVE LOGITS

ç±»åŀĭçļĦ

0.27

vod

0.26

senal

0.26

ulan

0.26

ISE

0.25

eeper

0.24

åŀĭåı·

0.24

yps

0.24

izio

0.23

etCode

0.23

Activations Density 0.022%

and

No Comments

No Known Activations