INDEX

Explanations

Internet text excerpts

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_1.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.1.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

gs

-0.31

iej

-0.30

ucs

-0.26

oglob

-0.26

sand

-0.25

Ð´Ð°ÐµÑĤ

-0.25

rens

-0.25

 knees

-0.25

äºĶå¤§

-0.25

<small

-0.24

POSITIVE LOGITS

 Blvd

0.29

olla

0.26

entry

0.25

 tÃ¹y

0.25

åħ¶å®ĥéĹ®é¢ĺ

0.24

çģ¿

0.24

çļĦéĤ£ä¸ª

0.24

ForKey

0.24

 ÑģÐ¾Ð±Ð¾Ð¹

0.23

icional

0.23

Activations Density 37.137%

Internet text excerpts

No Comments

No Known Activations