INDEX

Explanations

decline

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

oku

-0.30

 "+↵

-0.28

_ASM

-0.27

è¥Ł

-0.27

æĿĨ

-0.27

 killer

-0.26

ork

-0.26

ears

-0.25

endar

-0.25

ippers

-0.25

POSITIVE LOGITS

'__

0.25

orre

0.24

Caught

0.24

 preserve

0.24

 Noble

0.24

 preserved

0.24

 preservation

0.23

Ð±ÑĥÑĢ

0.23

unce

0.23

MeasureSpec

0.23

Activations Density 0.002%

decline

No Comments

No Known Activations