INDEX

Explanations

Citations and grammar

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

Attachments

-0.28

uiten

-0.27

ackBar

-0.26

æŀ§

-0.26

aten

-0.25

èĢĹè´¹

-0.25

 cost

-0.25

coli

-0.24

 Catal

-0.24

cost

-0.24

POSITIVE LOGITS

nab

0.32

éĥ¨éķ¿

0.28

alom

0.28

instant

0.28

 granny

0.28

Ya

0.26

omn

0.25

ä»»ä½ķå½¢å¼ı

0.25

çĽ

0.25

çº¸ä¸Ĭ

0.24

Activations Density 0.013%

Citations and grammar

No Comments

No Known Activations