INDEX

Explanations

Scientific/technical writing

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_14.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.14.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

éĢ

-0.28

ison

-0.28

ery

-0.28

ulant

-0.27

 adequate

-0.27

 proper

-0.26

 flavors

-0.26

 sufficient

-0.25

izable

-0.25

suf

-0.25

POSITIVE LOGITS

ç®Ń

0.26

.bind

0.25

bind

0.25

å®½å¸¦

0.25

æĲľ

0.25

ALIGN

0.24

 buses

0.24

ç¼´

0.24

.tail

0.24

 Ports

0.23

Activations Density 1.986%

Scientific/technical writing

No Comments

No Known Activations