INDEX

Explanations

news articles

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

 Regents

-0.27

Ð¾Ð¿ÑĢÐµÐ´ÐµÐ»ÐµÐ½

-0.26

:event

-0.26

.Space

-0.25

deo

-0.25

 ”↵↵

-0.25

 Country

-0.25

 region

-0.24

ungan

-0.24

inese

-0.24

POSITIVE LOGITS

ermann

0.27

Bi

0.27

Bi

0.26

äººæīįéĺŁä¼į

0.26

ful

0.25

æĹ©

0.25

éĢŁ

0.24

ibile

0.24

 stub

0.24

viz

0.24

Activations Density 0.147%

news articles

No Comments

No Known Activations