INDEX

Explanations

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_20.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.20.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

alley

-0.28

:\/\/

-0.24

éĺ³åİ¿

-0.23

 dynam

-0.23

åĪ¤

-0.23

::-

-0.23

unya

-0.23

direction

-0.23

::*

-0.23

 base

-0.22

POSITIVE LOGITS

Away

0.27

aro

0.26

ULO

0.26

_npc

0.25

IFO

0.25

npc

0.25

Embed

0.25

.embedding

0.24

åµĮ

0.24

.rpc

0.24

Activations Density 1.756%

advertisement

No Comments

No Known Activations