INDEX

Explanations

Michigan

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.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

callable

-0.29

é©·

-0.26

asher

-0.25

èµĦæľ¬ä¸»ä¹ī

-0.25

uya

-0.25

ulls

-0.24

åĩı

-0.24

asiswa

-0.24

quiz

-0.24

 nues

-0.24

POSITIVE LOGITS

vo

0.29

apr

0.26

 haul

0.26

 Sele

0.25

vo

0.25

oe

0.25

Î®

0.25

xdb

0.25

 inhabited

0.24

 Equal

0.24

Activations Density 0.001%

Michigan

No Comments

No Known Activations