INDEX

Explanations

numbers

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.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

ä¹ħ

-0.27

-member

-0.27

ippines

-0.26

|--

-0.24

-members

-0.24

çĸ¾çĹħçļĦ

-0.24

ÑĤÐ¾Ð½

-0.24

";"

-0.24

_initialized

-0.23

åĮºåĪ«

-0.23

POSITIVE LOGITS

lu

0.28

WAY

0.25

çº¹

0.25

fin

0.24

WAY

0.24

hdr

0.24

Fin

0.24

Way

0.23

ucc

0.23

Arrange

0.23

Activations Density 0.004%

numbers

No Comments

No Known Activations