INDEX

Explanations

producer

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

éĴŁ

-0.30

IFn

-0.27

ä½Ĩæĺ¯å¯¹äºİ

-0.26

ä½Ĩå¯¹äºİ

-0.26

Clock

-0.26

éĲĺ

-0.26

_IV

-0.25

ux

-0.25

HCI

-0.25

IPH

-0.24

POSITIVE LOGITS

 reint

0.26

heiten

0.26

 benchmarks

0.26

 whisk

0.25

heit

0.25

clusion

0.24

 franch

0.24

è¢«åĬ¨

0.24

æĹłç¼ĺ

0.24

 lÃ¡

0.23

Activations Density 0.005%

producer

No Comments

No Known Activations