INDEX

Explanations

controversy

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_0.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.0.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

(previous

-0.27

nie

-0.24

bject

-0.24

previous

-0.24

 comparisons

-0.24

 Previous

-0.24

 Comparable

-0.24

 previous

-0.24

æľīèī²

-0.23

ë¹Ī

-0.23

POSITIVE LOGITS

Ð°Ð½ÑĤ

0.26

olare

0.24

ector

0.23

ÑħÐ¾Ð´ÑıÑĤ

0.23

æŃ£å¸¸ä½¿çĶ¨

0.23

çļĦè¯Ŀé¢ĺ

0.23

ched

0.23

hoff

0.23

 addChild

0.23

keit

0.23

Activations Density 7.889%

controversy

No Comments

No Known Activations