INDEX

Explanations

Mixed code snippets/text

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

define

-0.30

NAL

-0.28

 equipments

-0.28

gings

-0.28

 Define

-0.28

ray

-0.27

 belongs

-0.27

ä¼¼çļĦ

-0.27

mai

-0.27

QA

-0.27

POSITIVE LOGITS

xFE

0.28

 Gaul

0.27

 systems

0.26

çĽ¸åħ³æĶ¿çŃĸ

0.26

Whilst

0.26

æŁ¥çľĭåħ¨æĸĩ

0.25

xfe

0.25

indre

0.25

-neutral

0.24

ilst

0.24

Activations Density 1.690%

Mixed code snippets/text

No Comments

No Known Activations