INDEX

Explanations

Negative impacts and discrimination

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.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®¡çĲĨæĿ¡ä¾ĭ

-0.28

 Intelli

-0.27

inton

-0.26

wagon

-0.26

äº¬

-0.25

å¥ĩè¿¹

-0.25

istrator

-0.24

åĳ±

-0.24

wag

-0.24

åĵ¦

-0.24

POSITIVE LOGITS

 vulnerable

0.26

.Style

0.25

æľ¬æĿ¥

0.25

éĤ£äºĽ

0.25

etails

0.25

 those

0.25

Routine

0.24

éĻĭ

0.24

ãĤ¹ãĤ¿ãĤ¤ãĥ«

0.24

ç«ĭä½ĵ

0.24

Activations Density 0.001%

Negative impacts and discrimination

No Comments

No Known Activations