INDEX

Explanations

sentence beginning words

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

æĥłæ°ĳ

-0.28

(Error

-0.25

ãĥªãĤ¹ãĥĪ

-0.25

å¸Ĥæ°ĳ

-0.25

.env

-0.25

StringValue

-0.24

å®£è¨Ģ

-0.24

åĨįå¤ļ

-0.24

å®¢æµģ

-0.24

PIT

-0.24

POSITIVE LOGITS

ira

0.32

ivo

0.27

ä¸ºä¸Ńå¿ĥ

0.26

è¿ľç¨ĭ

0.26

bet

0.25

plits

0.25

 Calder

0.24

(()

0.24

å¼Ĥ

0.24

dds

0.24

Activations Density 0.049%

sentence beginning words

No Comments

No Known Activations