INDEX

Explanations

mountains

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

ser

-0.27

/********************************************************************************

-0.26

!--

-0.25

Ļ¶

-0.24

ä¹¦è®°

-0.24

iant

-0.24

çľĭ

-0.24

æ³°

-0.23

Rei

-0.23

ç±³é¥Ń

-0.23

POSITIVE LOGITS

 resort

0.28

gam

0.27

 Daly

0.27

á»ĵng

0.27

exels

0.27

ungan

0.26

oola

0.26

æĪĸå¤ļ

0.25

æĹħæ¸¸

0.24

adium

0.24

Activations Density 0.011%

mountains

No Comments

No Known Activations