INDEX

Explanations

Locations/Organizations

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

 sectors

-0.27

raries

-0.27

 veget

-0.27

-sector

-0.26

ault

-0.25

assel

-0.25

ä¹ł

-0.24

æ³Į

-0.24

*=

-0.24

inea

-0.24

POSITIVE LOGITS

ADVERTISEMENT

0.27

antine

0.26

éĹ¯

0.25

ISTER

0.25

nock

0.25

Ã³

0.24

(Pos

0.23

 vandal

0.23

åħ·ä½ĵåĨħå®¹

0.23

å·¡èĪª

0.23

Activations Density 0.002%

Locations/Organizations

No Comments

No Known Activations