INDEX

Explanations

temperature

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

ä¸°æ»¡

-0.30

LOT

-0.28

æĭ³

-0.27

-0.26

 somewhere

-0.26

èµ·ä¼ı

-0.25

äº¤éĶĻ

-0.25

Buffer

-0.24

	Buffer

-0.24

éĤ£å°±æĺ¯

-0.24

POSITIVE LOGITS

-placeholder

0.28

_perms

0.28

_pressed

0.27

UsageId

0.26

SEQ

0.25

IRC

0.25

 Nullable

0.25

æĭ´

0.24

 sourceMappingURL

0.24

 Ð¾Ð¿Ñĭ

0.24

Activations Density 0.005%

temperature

No Comments

No Known Activations