INDEX

Explanations

answers

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¸Ľ

-0.27

éĿ¢çĽ®

-0.27

achusetts

-0.26

INGER

-0.26

iston

-0.25

_AI

-0.25

Qualifier

-0.24

æĦıä¹īä¸Ĭ

-0.24

QUAL

-0.24

ARING

-0.24

POSITIVE LOGITS

 elsewhere

0.32

èĤ¢ä½ĵ

0.27

war

0.27

 implied

0.27

çĲ´

0.26

tee

0.26

je

0.25

implicit

0.25

é¬¯

0.25

eva

0.24

Activations Density 0.004%

answers

No Comments

No Known Activations