INDEX

Explanations

General text snippets

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

Negative Logits

-cond

-0.25

veget

-0.25

contra

-0.24

 Cond

-0.24

è¿Ļè¾¹

-0.24

 invalid

-0.23

æĶ¾å°Ħ

-0.23

 contra

-0.23

uar

-0.23

ä½ķ

-0.23

POSITIVE LOGITS

cff

0.26

ç»Ĭ

0.26

pl

0.26

cerer

0.25

ëĬĺ

0.25

IGN

0.24

ieved

0.24

airs

0.24

ç¿³

0.24

limits

0.23

Activations Density 0.006%

General text snippets

No Known Activations