INDEX

Explanations

Encoding/formatting errors

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

 moon

-0.28

 tallest

-0.28

æĬĢæľ¯åĴĮ

-0.26

æ¯ıä¸ªæľĪ

-0.26

æľĪ

-0.26

æ¼Ķ

-0.25

å¹Ķ

-0.25

é¬¼

-0.25

 venue

-0.25

è¡¾

-0.25

POSITIVE LOGITS

cef

0.31

æĬ¥

0.30

lor

0.26

æĦıåĳ³

0.26

ju

0.25

 worker

0.25

(worker

0.25

loat

0.25

 Workers

0.24

{:

0.24

Activations Density 0.004%

Encoding/formatting errors

No Comments

No Known Activations