INDEX

Explanations

investment/contributions

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 favoured

-0.28

æľįä»İ

-0.27

çĤ¹äºĨ

-0.27

æ¯ĵ

-0.26

æ¯Ķäºļ

-0.26

æ²¡æĥ³åĪ°

-0.25

.Callback

-0.25

×Ļ×Ķ

-0.24

guard

-0.24

çµ®

-0.24

POSITIVE LOGITS

thon

0.27

åĬĥ

0.27

IntegerField

0.27

 scratch

0.25

ä½İä½į

0.25

ÄŁini

0.25

uxe

0.24

 ranks

0.24

 getField

0.24

åĲĦè¡Į

0.24

Activations Density 0.028%

investment/contributions

No Comments

No Known Activations