INDEX

Explanations

pre

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

Not in Any Lists

No Comments

Negative Logits

'article

-0.28

frame

-0.26

åºŃ

-0.25

Hall

-0.25

jal

-0.25

birth

-0.24

 present

-0.24

jac

-0.24

 haul

-0.23

 Hall

-0.23

POSITIVE LOGITS

ä¸ĢåĪ»

0.29

è£ħå¤ĩåĪ¶éĢł

0.28

åį§

0.27

tol

0.27

 Developed

0.27

ervice

0.27

ç»ĵæŀľæĺ¾ç¤º

0.26

cil

0.26

éħįç½®

0.26

enting

0.26

Activations Density 0.787%

pre

No Comments

No Known Activations