INDEX

Explanations

say "temperature"

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

NCY

-0.27

 wheel

-0.26

tte

-0.25

çı©

-0.25

å²³

-0.25

æĴĻ

-0.25

 hand

-0.25

br

-0.24

Cleanup

-0.24

 velocities

-0.24

POSITIVE LOGITS

èĴŁ

0.27

éħĲ

0.25

åħ·æľīä¸Ģå®ļ

0.24

Pot

0.23

Intern

0.23

 denen

0.23

Êĥ

0.23

LinkId

0.23

 dansk

0.23

 Tencent

0.23

Activations Density 0.013%

say "temperature"

No Comments

No Known Activations