INDEX

Explanations

rest

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

isser

-0.28

 budd

-0.28

è¦ģä¹Ī

-0.26

anium

-0.25

"indices

-0.25

bsub

-0.25

 Britann

-0.25

RESSION

-0.25

UB

-0.25

vidence

-0.24

POSITIVE LOGITS

tract

0.27

mel

0.26

LowerCase

0.26

 nonexistent

0.26

éĴŁ

0.23

éģ¿å¼Ģ

0.23

mel

0.23

 competit

0.23

ä¹°çļĦ

0.23

 column

0.23

Activations Density 0.309%

rest

No Comments

No Known Activations