INDEX

Explanations

taxes

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

èĢį

-0.27

odu

-0.27

adr

-0.25

áº¡n

-0.25

oute

-0.25

 lite

-0.25

ä»ĭ

-0.24

fortunate

-0.24

erez

-0.24

rowse

-0.23

POSITIVE LOGITS

atos

0.28

çŁ¥è¯ĨçĤ¹

0.27

 Ahead

0.27

ahead

0.26

acent

0.26

æĬķèµĦé¢Ŀ

0.26

 ahead

0.25

ritos

0.25

Ahead

0.25

è¯·èģĶç³»

0.25

Activations Density 0.002%

taxes

No Comments

No Known Activations