INDEX

Explanations

Code and file paths

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

.qq

-0.27

ÑĩÑĥ

-0.26

urre

-0.26

 Baghd

-0.25

è¬

-0.25

åĨĬ

-0.24

è«

-0.24

 Junior

-0.24

testdata

-0.23

 Conf

-0.23

POSITIVE LOGITS

ç´¢

0.29

Tur

0.28

 band

0.28

çŁ¢

0.27

//{{

0.26

band

0.26

straction

0.26

egral

0.26

 centres

0.25

 pain

0.25

Activations Density 0.003%

Code and file paths

No Comments

No Known Activations