INDEX

Explanations

conversational text

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ç¦ģå¿Į

-0.28

 tecn

-0.27

ossa

-0.27

å½ĵæĹ¶

-0.27

èĵ¼

-0.27

 Deadline

-0.26

BIN

-0.26

uards

-0.26

ption

-0.25

.AddRange

-0.25

POSITIVE LOGITS

eria

0.26

rips

0.25

åı«

0.25

icom

0.24

attachments

0.24

 mentions

0.24

æªĶ

0.23

ãģ¼

0.23

 Bail

0.23

ç¹¼

0.23

Activations Density 0.000%

conversational text

No Comments

No Known Activations