INDEX

Explanations

or

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

oot

-0.29

æī¬

-0.28

XCT

-0.27

lev

-0.26

eam

-0.26

éĿł

-0.25

sect

-0.24

ä»²è£ģ

-0.24

nehmer

-0.24

.obtain

-0.24

POSITIVE LOGITS

icates

0.27

ooke

0.25

éºĴ

0.24

è±³

0.23

Ĳľç´¢

0.23

å¹´åĨħ

0.23

ERNEL

0.23

tries

0.23

 noses

0.22

æĬ¥éĶĢ

0.22

Activations Density 0.001%

or

No Comments

No Known Activations