INDEX

Explanations

from

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

command

-0.25

 gear

-0.25

_cursor

-0.24

æĽ²

-0.24

æıĴ

-0.24

æĬ½è±¡

-0.23

ä¼Ĳ

-0.23

è´´è¿ĳ

-0.23

å®¶çĶ¨

-0.23

 discover

-0.23

POSITIVE LOGITS

amat

0.34

alt

0.28

 thoÃ¡ng

0.26

ÙĪØ·

0.26

 Erect

0.26

 Column

0.25

ephy

0.25

orderid

0.25

æıĲåĲį

0.24

ablish

0.24

Activations Density 0.002%

from

No Comments

No Known Activations