INDEX

Explanations

brain

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

åħ¶å®ĥéĹ®é¢ĺ

-0.27

ofi

-0.27

vol

-0.27

pson

-0.25

INC

-0.25

ished

-0.24

åİħ

-0.24

å¼ķ

-0.24

ince

-0.24

pel

-0.23

POSITIVE LOGITS

å¼ıçļĦ

0.27

ctl

0.27

Routes

0.27

dle

0.27

åĿ³

0.25

irm

0.25

atedRoute

0.24

atted

0.24

çĥ

0.23

å£ģåŀĴ

0.23

Activations Density 0.047%

brain

No Comments

No Known Activations