INDEX

Explanations

people

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ä»²è£ģ

-0.26

yc

-0.26

ement

-0.26

äºĴ

-0.25

äºĭ

-0.25

ÙĪØ±Ø¯

-0.24

**

-0.24

us

-0.24

èıľ

-0.24

ltre

-0.24

POSITIVE LOGITS

åĬ¬

0.27

 change

0.26

intage

0.26

 CHANGE

0.26

èŃĺ

0.25

 Newtown

0.25

-change

0.25

WithType

0.25

 Soros

0.25

abouts

0.24

Activations Density 0.209%

people

No Comments

No Known Activations