INDEX

Explanations

ary

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

ëł¨

-0.27

INDER

-0.24

occo

-0.24

 Bender

-0.24

 rall

-0.24

cee

-0.24

é¹¤

-0.24

å¦ĤæľŁ

-0.24

/by

-0.23

Against

-0.23

POSITIVE LOGITS

èĦ±

0.30

anka

0.28

Ã©nom

0.27

 Ð½Ð°ÑĤÑĥÑĢÐ°Ð»ÑĮÐ½

0.27

è½½

0.27

TickCount

0.26

åľ¨å®¶

0.26

chemes

0.26

-inverse

0.25

åĢĴ

0.24

Activations Density 0.000%

ary

No Comments

No Known Activations