INDEX

Explanations

health

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

å¹Ķ

-0.26

æĦıè§ģ

-0.26

ssue

-0.25

ç¤º

-0.25

 spokesperson

-0.25

æ¯ģ

-0.24

flower

-0.24

.basicConfig

-0.24

éĤ£æł·çļĦ

-0.24

_framework

-0.23

POSITIVE LOGITS

ption

0.27

 Ð³Ð°ÑĢ

0.27

 Peyton

0.27

é£İéĽ¨

0.26

idges

0.25

IVES

0.25

èĮĦåŃĲ

0.25

çĲµ

0.24

è¢Ĥ

0.24

hints

0.23

Activations Density 0.784%

health

No Comments

No Known Activations