INDEX

Explanations

Internet data/text

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

anic

-0.27

ovich

-0.26

hausen

-0.25

æĳĩäºĨ

-0.25

OLS

-0.24

amat

-0.24

ModelAttribute

-0.24

 mixing

-0.24

æ¨¹

-0.24

elo

-0.24

POSITIVE LOGITS

çľĭä½ł

0.28

iors

0.27

soever

0.26

osc

0.25

ItemId

0.25

âĢ¦↵↵↵↵

0.25

_er

0.24

 Bair

0.24

à°¦

0.24

 serialVersionUID

0.23

Activations Density 0.034%

Internet data/text

No Comments

No Known Activations