INDEX

Explanations

Police

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

å®ŀä½ĵ

-0.27

ervo

-0.25

 ovarian

-0.24

 treasure

-0.24

getResource

-0.23

alysis

-0.23

ä½Ĩå¥¹

-0.23

atisfied

-0.23

Performed

-0.23

èĬ

-0.23

POSITIVE LOGITS

go

0.26

go

0.25

Ð²Ð¾ÑĢÐ¾ÑĤ

0.25

 incident

0.25

 premise

0.25

 Warn

0.24

{?

0.24

èĥĮæĻ¯

0.24

(go

0.23

logan

0.23

Activations Density 0.007%

Police

No Comments

No Known Activations