INDEX

Explanations

Questions and explanations

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

è§£éĩĬ

-0.55

 definitions

-0.50

 gloss

-0.49

 explanations

-0.47

 explaining

-0.46

 explained

-0.46

è§£éĩĭ

-0.44

 Definitions

-0.44

 explain

-0.43

definitions

-0.41

POSITIVE LOGITS

 graph

0.27

åĢ¾

0.27

RNA

0.27

éĻĲæĹ¶

0.26

orry

0.26

adian

0.26

apyrus

0.26

ayÄ±

0.26

graph

0.25

RNA

0.25

Activations Density 0.001%

Questions and explanations

No Comments

No Known Activations

Questions and explanations

No Comments

No Known Activations