INDEX

Explanations

space

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 trá»ĭ

-0.26

ilst

-0.25

ë¢°

-0.25

éĻ¶

-0.24

 Performing

-0.24

iker

-0.23

åįİå°Ķ

-0.23

ä¼Ļä¼´åħ³ç³»

-0.23

bri

-0.23

 Bath

-0.23

POSITIVE LOGITS

ç©ºéĹ´

1.16

 space

1.15

çļĦç©ºéĹ´

0.96

-space

0.91

space

0.91

ç©ºéĸĵ

0.90

 Space

0.90

Space

0.89

_space

0.84

ãĤ¹ãĥļãĥ¼ãĤ¹

0.84

Activations Density 0.011%

space

No Comments

No Known Activations