INDEX

Explanations

code/technical documentation

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

ä¸īæĸ¹

-0.24

æ¡Į

-0.23

lap

-0.23

å®ķ

-0.23

(ph

-0.22

Nam

-0.22

...",↵

-0.22

 $č↵

-0.22

Getting

-0.21

çīĪæĿĥå½Ĵ

-0.21

POSITIVE LOGITS

vla

0.25

ales

0.25

hea

0.23

ufe

0.22

lef

0.22

 =========================================================================

0.22

|#

0.22

uchos

0.22

 fittings

0.22

Cls

0.21

Activations Density 0.005%

code/technical documentation

No Comments

No Known Activations