INDEX

Explanations

period

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_20.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.20.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

çº§ä»¥ä¸Ĭ

-0.27

MR

-0.27

actly

-0.25

ewe

-0.25

 Â«

-0.24

edly

-0.24

à¸ªà¸§

-0.24

Retrieve

-0.24

mr

-0.24

ngr

-0.24

POSITIVE LOGITS

dur

0.29

çİĩ

0.29

 rate

0.28

 calc

0.27

æĵįä½ľ

0.27

reta

0.26

dur

0.26

Dur

0.26

ment

0.25

Ops

0.25

Activations Density 1.692%

period

No Known Activations