INDEX

Explanations

Unusual text

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ÑħÐ¾Ð¶

-0.27

ome

-0.25

è£ħè½½

-0.25

utron

-0.25

aybe

-0.24

 safeg

-0.23

è£Ŀ

-0.23

>Loading

-0.23

pto

-0.23

áº¡o

-0.23

POSITIVE LOGITS

vos

0.35

è§ģè¯ģ

0.26

traditional

0.26

-align

0.26

 traditional

0.26

 abandoned

0.26

ç«Ļåľ¨

0.25

 inside

0.24

èľķ

0.24

è³

0.24

Activations Density 0.023%

Unusual text

No Comments

No Known Activations