INDEX

Explanations

ag

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

åĭĥ

-0.26

éħįå¥Ĺ

-0.26

 Ð¿Ð°ÑĢÑĤ

-0.25

pictured

-0.25

 succeeding

-0.25

 discovery

-0.25

è¯±å¯¼

-0.24

å¤įæ´»

-0.24

æŃĮ

-0.24

dorf

-0.23

POSITIVE LOGITS

 Input

0.29

å¿ĥæĦı

0.28

-leg

0.27

åĨ¢

0.26

è¯¯

0.26

Input

0.25

Leg

0.25

çĽ®ãģ«

0.24

çĸĶ

0.24

.addAction

0.24

Activations Density 0.021%

ag

No Comments

No Known Activations