INDEX

Explanations

decided

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

fatal

-0.28

ibble

-0.25

 newPath

-0.25

 carrier

-0.25

GroupName

-0.25

.Future

-0.25

 Simulator

-0.25

<dd

-0.24

å¥

-0.24

OB

-0.24

POSITIVE LOGITS

-outline

0.27

å·¥èīº

0.27

ded

0.26

ded

0.26

æĹłéľĢ

0.25

æİ¨çĲĨ

0.25

ensen

0.24

ç¶ļãģį

0.24

çĽ¸éĢļ

0.24

å¤§äºº

0.24

Activations Density 0.002%

decided

No Comments

No Known Activations