INDEX

Explanations

(

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

 broadcasts

-0.26

ack

-0.25

ack

-0.25

locate

-0.24

 Broadcasting

-0.24

è¡¥åħħ

-0.24

 dormant

-0.24

å¹¿æĴŃ

-0.24

 bedtime

-0.24

encies

-0.24

POSITIVE LOGITS

åĵ²

0.28

rob

0.27

spr

0.25

deen

0.25

heimer

0.25

glas

0.24

 hence

0.24

çĬ¹

0.23

çķļ

0.23

<![

0.23

Activations Density 0.150%

(

No Comments

No Known Activations