INDEX

Explanations

coding related text

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_31.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.31.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

åħĨ

-0.28

MAND

-0.28

çĤ¸å¼¹

-0.28

ä¿¾

-0.25

chod

-0.24

Tpl

-0.24

åºŀ

-0.24

-ring

-0.24

æīĵåĵį

-0.24

 Ending

-0.23

POSITIVE LOGITS

ANA

0.28

ana

0.28

state

0.28

 createState

0.28

 reversible

0.26

 state

0.26

UC

0.25

itor

0.25

emp

0.24

aco

0.24

Activations Density 0.046%

coding related text

No Known Activations