INDEX

Explanations

elastic

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

åľ¨åĵª

-0.28

 cá»©

-0.28

éĤ£ä½į

-0.26

æıĲåĩºçļĦ

-0.25

 rude

-0.25

çĶŁåŃĺ

-0.25

 narrowly

-0.24

éĵ§

-0.23

åĪ°æĿ¥

-0.23

ologna

-0.23

POSITIVE LOGITS

éĻĲåº¦

0.27

çŀ¬

0.26

ancement

0.25

æ¬łç¼º

0.25

MethodManager

0.25

ahi

0.25

å¤§å®¶åĪĨäº«

0.24

odia

0.24

filer

0.24

idity

0.24

Activations Density 0.005%

elastic

No Comments

No Known Activations