INDEX

Explanations

composing/creation

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.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

uture

-0.28

 labor

-0.27

èĭķ

-0.27

Ð¾ÑģÑĤÐ¾Ñı

-0.27

ĽĦ

-0.27

spl

-0.26

Spl

-0.26

ä½ľåĿĬ

-0.26

ç¼ķ

-0.25

 machining

-0.25

POSITIVE LOGITS

åıįè½¬

0.27

ibo

0.27

 basÄ±n

0.25

autop

0.24

 misunderstood

0.24

sal

0.24

nau

0.24

 ÑĥÑģÑĤÐ°Ð½Ð¾Ð²Ð»ÐµÐ½

0.24

ç©ºæ°ĶåĩĢåĮĸ

0.23

NA

0.23

Activations Density 0.031%

composing/creation

No Comments

No Known Activations