INDEX

Explanations

0

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

ariate

-0.30

aton

-0.28

ÐĲÐĿ

-0.27

å¤ļäºº

-0.27

çĥŁçģ«

-0.26

ecast

-0.26

makt

-0.26

 Boyd

-0.24

ç¿»è¯ĳ

-0.24

è¼©

-0.24

POSITIVE LOGITS

.objects

0.26

 indices

0.26

PATCH

0.25

erver

0.25

ä¿ĿéĻ©

0.25

 jack

0.24

.patch

0.24

æ·¡

0.24

 PATCH

0.24

 positions

0.24

Activations Density 1.158%

0

No Comments

No Known Activations