INDEX

Explanations

ghost

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

nown

-0.28

èĭķ

-0.28

IKE

-0.26

å³Ĵ

-0.26

æı

-0.26

å¯¹éĿ¢

-0.25

ITICAL

-0.25

.unknown

-0.24

 dope

-0.24

ĳľ

-0.24

POSITIVE LOGITS

 tempered

0.27

Earn

0.27

_bundle

0.25

 provisional

0.24

spaces

0.24

cs

0.23

//*[

0.23

otec

0.23

 Fraction

0.23

æĹłæĦı

0.23

Activations Density 0.055%

ghost

No Comments

No Known Activations