INDEX

Explanations

"on one hand"

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_9.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.9.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 scar

-0.30

scar

-0.29

future

-0.29

Future

-0.28

inch

-0.27

èĳ¬

-0.27

æĭ¯

-0.27

 subs

-0.26

æħĪåĸĦ

-0.25

 Scar

-0.25

POSITIVE LOGITS

 Cowboy

0.30

çįł

0.26

 Cowboys

0.26

 RESERVED

0.26

æĵħ

0.25

 nutrit

0.25

curity

0.25

 endings

0.25

bral

0.25

onga

0.24

Activations Density 0.033%

"on one hand"

No Comments

No Known Activations