INDEX

Explanations

front

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

TES

-0.29

ãĤ«ãĥĨ

-0.27

edBy

-0.27

ä¹ł

-0.26

ppers

-0.26

ÐĹÐ°

-0.24

æŀĦæĪĲäºĨ

-0.24

odge

-0.24

 experiÃªncia

-0.24

ksam

-0.23

POSITIVE LOGITS

ä¸»ä¹īæĢĿæĥ³

0.32

à¤ĸ

0.27

bon

0.26

 subjective

0.26

èĽ®

0.26

å¥½åĿı

0.25

 Savage

0.25

åĿı

0.25

xi

0.24

æ²¼

0.24

Activations Density 0.116%

front

No Comments

No Known Activations