INDEX

Explanations

years

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

protect

-0.29

yll

-0.26

abin

-0.26

åİĦ

-0.25

brain

-0.25

å¹³æĸ¹

-0.25

åŀĦ

-0.25

afort

-0.25

orious

-0.25

VIR

-0.24

POSITIVE LOGITS

 Ð²ÑĭÐ¿

0.26

ä¸ĵæłı

0.25

å±ķ

0.25

 Sleeping

0.25

zier

0.25

åĢĻ

0.24

colo

0.24

 anesthesia

0.24

heimer

0.24

ÐµÐ²Ð°

0.24

Activations Density 0.099%

years

No Comments

No Known Activations