INDEX

Explanations

dehydration/hydration

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

rollo

-0.29

partment

-0.28

 compreh

-0.27

edom

-0.27

ç»¼åĲĪ

-0.27

Tick

-0.26

.hashCode

-0.24

 aspir

-0.24

/authentication

-0.24

parsers

-0.24

POSITIVE LOGITS

èĹ¿

0.28

å·¥åħ·

0.27

èĥ¼

0.27

æĶ¹è¿Ľ

0.26

etz

0.25

ìĦł

0.25

åĽł

0.25

iswa

0.25

 preceded

0.25

die

0.25

Activations Density 0.068%

dehydration/hydration

No Comments

No Known Activations