INDEX

Explanations

och

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

ipi

-0.29

 virtual

-0.28

formatter

-0.26

åĩĨç¡®æĢ§

-0.26

å¹ķ

-0.25

 hood

-0.25

éĩĩ

-0.25

 qualitÃł

-0.24

 State

-0.24

 interviewed

-0.24

POSITIVE LOGITS

adier

0.27

è¡·

0.27

iable

0.27

<![

0.26

 Encore

0.26

ç¶ļ

0.26

 Coch

0.25

ä»¥ä¹łè¿ĳå¹³

0.25

evin

0.25

 Coinbase

0.25

Activations Density 0.071%

och

No Comments

No Known Activations