INDEX

Explanations

Barriers and boundaries

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_22.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.22.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

é¼»

-0.27

ivalence

-0.26

Negative

-0.25

å¹´èµ·

-0.25

erta

-0.24

immune

-0.24

operative

-0.24

 Vive

-0.24

è¾Ĺ

-0.24

ÑģÐ°Ð»

-0.24

POSITIVE LOGITS

ä¿ĿæĬ¤

0.39

 protect

0.37

ä¿ĿèŃ·

0.31

 Protect

0.31

 protecting

0.31

protect

0.30

éļĶç¦»

0.30

 protection

0.29

 Sheet

0.29

 sheet

0.28

Activations Density 0.055%

Barriers and boundaries

No Comments

No Known Activations