INDEX

Explanations

L

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.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

.about

-0.27

.light

-0.25

 professionalism

-0.25

ÑģÑĤÐµÑĢ

-0.24

 dislike

-0.24

è½¬åĬ¨

-0.24

æīŃ

-0.24

ä¸ĵçĶ¨

-0.24

pha

-0.23

akedown

-0.23

POSITIVE LOGITS

çģĮ

0.32

xico

0.31

 Logic

0.28

 logic

0.26

logic

0.26

 Pres

0.25

Pet

0.25

 Implicit

0.25

pres

0.24

 PRES

0.24

Activations Density 0.005%

L

No Comments

No Known Activations