INDEX

Explanations

built

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

å¾Ĺèµ·

-0.31

.Fire

-0.25

ä»·

-0.24

getStore

-0.24

é¹

-0.23

/run

-0.23

atÄĥ

-0.23

postal

-0.23

inceton

-0.23

utura

-0.23

POSITIVE LOGITS

åĲ¦åĪĻ

0.30

sam

0.28

 alike

0.26

ilder

0.26

èĻ½è¯´

0.25

tdown

0.24

æ·¹

0.24

çĪ°

0.24

IMS

0.24

âķ¯

0.24

Activations Density 0.007%

built

No Comments

No Known Activations