INDEX

Explanations

per

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.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

åĲ¬äºĨ

-0.31

 BorderLayout

-0.27

 URLRequest

-0.26

 Diploma

-0.25

Vol

-0.25

çĲĨè§£åĴĮ

-0.25

uite

-0.25

 Governors

-0.24

æĢ»è®¡

-0.24

ä½Ŀ

-0.23

POSITIVE LOGITS

å¹³åı°

0.28

ipi

0.27

onnement

0.27

å¹³åı°ä¸Ĭ

0.26

NodeType

0.26

iteration

0.26

ewise

0.26

-platform

0.25

ocy

0.24

 platform

0.24

Activations Density 0.009%

per

No Comments

No Known Activations