INDEX

Explanations

information or data

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

Dom

-0.27

å£¹

-0.26

-dom

-0.25

Tac

-0.25

 accommodations

-0.25

 Accom

-0.24

iert

-0.24

åħīéĺ´

-0.24

.enabled

-0.24

.lat

-0.24

POSITIVE LOGITS

çĲĨä¼ļ

0.29

 threatened

0.27

åĨ²åĩ»

0.26

/ajax

0.26

ANGO

0.25

bern

0.25

 foreseeable

0.25

 Redistributions

0.25

 wohl

0.24

-outline

0.24

Activations Density 0.100%

information or data

No Comments

No Known Activations

information or data

No Comments

No Known Activations