INDEX

Explanations

ke

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_2.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.2.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

ades

-0.28

 FÃ¶rder

-0.25

parator

-0.25

IFI

-0.24

ifi

-0.24

 scrapy

-0.24

æįº

-0.24

akan

-0.24

APH

-0.24

ç¯¡

-0.23

POSITIVE LOGITS

é¥¼

0.29

 humble

0.27

ä¸īé¡¹

0.27

away

0.27

é¥¯

0.25

 mantle

0.25

-main

0.24

/\

0.24

èĥĮåĲİçļĦ

0.24

omat

0.23

Activations Density 51.142%

ke

No Comments

No Known Activations