INDEX

Explanations

neuroscience and fascination

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_0.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.0.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

evin

-0.26

åľ£è¯ŀ

-0.26

åľ¨æĪĳçļĦ

-0.25

åľ£è¯ŀèĬĤ

-0.25

 ministry

-0.24

ETCH

-0.24

IPH

-0.24

éļĲç§ģ

-0.24

åĮĿ

-0.23

IgnoreCase

-0.23

POSITIVE LOGITS

tera

0.26

ÙĬØ±Ø©

0.25

ter

0.25

äººæ°ĳ

0.25

å¡ĺ

0.24

But

0.23

çĵ¶

0.23

ãģ°ãģĭãĤĬ

0.23

å¹ķ

0.22

æ´±

0.22

Activations Density 3.190%

neuroscience and fascination

No Comments

No Known Activations