INDEX

Explanations

Quantities and associations

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ãĥ¼ãĥł

-0.32

uang

-0.27

å¼ķåıĳäºĨ

-0.26

ç«ĸ

-0.26

é«ĺçŃī

-0.26

itor

-0.26

å¼ķèµ·äºĨ

-0.26

ê¸°ëĬĶ

-0.25

ofile

-0.25

entes

-0.24

POSITIVE LOGITS

 refinement

0.25

 Else

0.25

.jackson

0.25

é»ľ

0.24

ressing

0.23

opian

0.23

 therefore

0.23

 Changes

0.23

 Stellar

0.22

Changes

0.22

Activations Density 0.004%

Quantities and associations

No Comments

No Known Activations