INDEX

Explanations

wife

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

å½Ĺ

-0.26

 organised

-0.26

è··

-0.25

äº¤

-0.25

scar

-0.25

bsite

-0.25

 ordered

-0.25

ä¹°è½¦

-0.24

 large

-0.24

ordered

-0.24

POSITIVE LOGITS

æºŁ

0.28

æĵį

0.27

 drift

0.27

 Kont

0.26

etSocketAddress

0.26

ä¸Ģåı·

0.25

 Sears

0.25

.credentials

0.25

åıĤ

0.25

 Mold

0.24

Activations Density 0.001%

wife

No Comments

No Known Activations