INDEX

Explanations

Formal writing

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

é©¾

-0.29

acional

-0.26

ä¾¬

-0.26

è¿Ļè¯Ŀ

-0.26

 Deal

-0.25

msp

-0.25

ioned

-0.25

fsp

-0.25

çĶŁäº§çĶŁæ´»

-0.24

DTD

-0.24

POSITIVE LOGITS

Seattle

0.28

åľ°çĤ¹

0.28

[--

0.26

çĬĢ

0.26

æĥ³åĬŀæ³ķ

0.25

 extent

0.24

 Partial

0.23

.ab

0.23

 Metals

0.23

Partial

0.23

Activations Density 0.151%

Formal writing

No Comments

No Known Activations