INDEX

Explanations

housing

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ersistence

-0.27

 maximizing

-0.25

uide

-0.24

ÐºÑĢÐ¾Ð²

-0.23

luet

-0.23

çĶº

-0.23

è½¦ä½į

-0.23

posite

-0.23

ç±³

-0.23

çºªå§ĶçĽĳå§Ķ

-0.23

POSITIVE LOGITS

inters

0.27

æŀ¶

0.26

\TestCase

0.25

æłı

0.25

::__

0.25

ãģĻãģİ

0.25

(robot

0.25

éĹª

0.24

æīİ

0.24

ĥģ

0.24

Activations Density 0.003%

housing

No Comments

No Known Activations