INDEX

Explanations

full

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

Not in Any Lists

No Comments

Negative Logits

æİĴåĩº

-0.28

arie

-0.27

imet

-0.26

acet

-0.25

Collider

-0.25

(Tag

-0.24

yr

-0.24

cmc

-0.23

Abs

-0.23

FN

-0.23

POSITIVE LOGITS

 complexity

0.32

å¯¹ä¸įèµ·

0.31

NESS

0.30

itude

0.28

çİ¯çĲĥ

0.28

undance

0.28

 variety

0.28

ness

0.28

 Variety

0.27

 magnitude

0.27

Activations Density 0.017%

full

No Comments

No Known Activations