INDEX

Explanations

books and introductions

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

.er

-0.29

áº¡ng

-0.27

oted

-0.27

phies

-0.26

itung

-0.25

çº©

-0.24

Slo

-0.24

bucket

-0.24

tober

-0.24

 friendships

-0.23

POSITIVE LOGITS

è´Ł

0.32

å®«

0.28

 reality

0.26

å½Ĵ

0.26

ç¡ħ

0.26

åºŃ

0.24

å¤ĸè§Ĥ

0.24

ente

0.24

è²ł

0.24

äººå®¶

0.24

Activations Density 0.005%

books and introductions

No Comments

No Known Activations