INDEX

Explanations

scientific/technical texts

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ç³»

-0.28

ç»ĥ

-0.27

ocal

-0.26

loy

-0.26

èĢĮæĺ¯

-0.25

 blaze

-0.24

 naturally

-0.24

aturated

-0.23

ä¾ª

-0.23

ä»ĺãģįåĲĪ

-0.23

POSITIVE LOGITS

åĽ«

0.29

éĩįè¦ģåĨħå®¹

0.25

 Ripple

0.25

-duration

0.25

 Needed

0.24

 bunk

0.24

éĤª

0.24

_firstname

0.24

PropertyName

0.24

Facing

0.24

Activations Density 0.093%

scientific/technical texts

No Comments

No Known Activations