INDEX

Explanations

Technical documentation/computer systems

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

æľº

-0.32

 bordel

-0.32

lin

-0.30

orus

-0.30

cludes

-0.28

áº¬

-0.26

listed

-0.26

 bÄĻdÄħ

-0.25

pageTitle

-0.25

 Thought

-0.24

POSITIVE LOGITS

’an

0.28

çĥĽ

0.26

iben

0.26

 Scheme

0.26

Deferred

0.25

íģĲ

0.25

åıĪè¢«

0.25

.Scheme

0.24

æł·æĿ¿

0.24

é£İæ³¢

0.24

Activations Density 0.010%

Technical documentation/computer systems

No Comments

No Known Activations