INDEX

Explanations

infertility

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

çĤ¹äºĨ

-0.28

 nghi

-0.25

æĭĲ

-0.25

 Bless

-0.24

 recalled

-0.23

åħ³éĶ®æĬĢæľ¯

-0.23

 Bernstein

-0.23

vard

-0.23

åħ³éĶ®

-0.23

æĦŁåħ´è¶£çļĦ

-0.23

POSITIVE LOGITS

pter

0.32

\`

0.28

 building

0.27

-building

0.26

 spit

0.26

 spiral

0.26

pta

0.25

ä¹ĥ

0.25

åĨħé©¬

0.25

inho

0.25

Activations Density 0.003%

infertility

No Comments

No Known Activations