INDEX

Explanations

regulations and different languages

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

mez

-0.29

atten

-0.28

pard

-0.27

ä¸Ńåħ³

-0.26

ITU

-0.26

awei

-0.26

 notebook

-0.25

 Decomp

-0.25

å°ĺ

-0.25

peria

-0.24

POSITIVE LOGITS

èı½

0.32

 minHeight

0.27

Ger

0.27

egrated

0.25

 stick

0.25

æĪİ

0.25

 hath

0.24

eut

0.24

 dedicate

0.24

ToFit

0.24

Activations Density 0.028%

regulations and different languages

No Comments

No Known Activations