INDEX

Explanations

biology and environment

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.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

Benchmark

-0.29

ãģªãģĭ

-0.27

ãģĸ

-0.27

slope

-0.27

bond

-0.26

/rand

-0.26

 newIndex

-0.26

ÙĦØ§ÙĤØ©

-0.26

ç¶ļãģįãĤĴèªŃãĤĢ

-0.25

enschaft

-0.24

POSITIVE LOGITS

Ved

0.31

&s

0.27

 intern

0.27

æ±¹

0.27

.live

0.25

&m

0.25

 graph

0.24

é¥±æ»¡

0.24

cul

0.23

consider

0.23

Activations Density 0.002%

biology and environment

No Comments

No Known Activations