INDEX

Explanations

organic

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

 Mines

-0.27

utow

-0.26

atos

-0.26

 mines

-0.26

ieres

-0.25

 traces

-0.25

ªĮ

-0.25

 bets

-0.24

reserved

-0.24

 anchors

-0.24

POSITIVE LOGITS

èµĦæºĲæķ´åĲĪ

0.28

å®¹

0.27

éĹªçĶµ

0.26

NodeId

0.26

 recurs

0.25

éĹª

0.24

 likely

0.24

lider

0.24

æķ´åĲĪ

0.24

oge

0.24

Activations Density 0.001%

organic

No Known Activations