INDEX

Explanations

appl

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

 Adult

-0.30

 adult

-0.30

æīĭä¸ŃçļĦ

-0.29

bec

-0.27

 itself

-0.26

æīĭä¸Ń

-0.26

nor

-0.26

 feeder

-0.25

æľ¬èº«çļĦ

-0.25

æ»Ķ

-0.24

POSITIVE LOGITS

renc

0.28

arnation

0.28

å¹´åĨħ

0.27

 pray

0.25

ãĥ¬ãĥ³

0.25

thin

0.25

 Budd

0.25

pray

0.25

 Ranked

0.24

tam

0.24

Activations Density 0.054%

appl

No Comments

No Known Activations