INDEX

Explanations

local

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_22.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.22.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ä¸ĭåįĬ

-0.28

atively

-0.28

æ²¹èħ»

-0.28

asty

-0.26

win

-0.26

 ÐºÐ¾Ð¶

-0.25

-devel

-0.25

 confuse

-0.25

urons

-0.25

uren

-0.25

POSITIVE LOGITS

 Spoon

0.26

PUR

0.26

ition

0.25

 Harbor

0.25

ResourceManager

0.25

ServiÃ§o

0.23

 ofType

0.23

 Edge

0.23

æ¡¥

0.23

GraphNode

0.23

Activations Density 0.008%

local

No Comments

No Known Activations