INDEX

Explanations

Start

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

çĶ·å¥³

-0.28

èĦ¸

-0.28

æĴ°

-0.27

acre

-0.27

èĢģä¹¡

-0.26

åĲ¬çĿĢ

-0.26

 Sing

-0.25

 added

-0.25

æ·¦

-0.25

utsch

-0.25

POSITIVE LOGITS

çļĦè·Ŀç¦»

0.26

edList

0.26

è¿Ļéĥ¨åĪĨ

0.26

åħ¬çĽĬæĢ§

0.26

phis

0.26

inally

0.25

è¿ĻäºĽä¸ľè¥¿

0.25

 Ð¿ÑĢÐ¾Ñģ

0.25

phas

0.24

redni

0.23

Activations Density 0.008%

Start

No Comments

No Known Activations