INDEX

Explanations

research

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

á»«

-0.28

åĨħéĥ¨

-0.27

urses

-0.27

åįģåŃĹ

-0.27

å¤ĸåĽ´

-0.26

åħ§éĥ¨

-0.26

ãĤµãĥ³

-0.26

PointSize

-0.25

subclass

-0.25

 reap

-0.24

POSITIVE LOGITS

 cott

0.28

oney

0.27

åıªè¦ģä½ł

0.26

DT

0.25

å°ıåº·

0.24

 Mayer

0.24

ME

0.24

 bubble

0.24

 recur

0.24

 gloss

0.23

Activations Density 0.011%

research

No Comments

No Known Activations