INDEX

Explanations

3

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

åıĳ

-0.30

illa

-0.27

çĻ

-0.26

/=

-0.26

 åıĳ

-0.26

æ¿Ģç´ł

-0.25

 taxed

-0.25

imize

-0.25

ÐĿÐ«

-0.25

listening

-0.25

POSITIVE LOGITS

-seat

0.27

 heav

0.27

 roman

0.26

çļĦåİŁåĪĻ

0.25

 ayud

0.25

Principal

0.25

	help

0.25

 STREAM

0.25

 namely

0.24

ä¼°åĢ¼

0.24

Activations Density 0.004%

3

No Comments

No Known Activations