INDEX

Explanations

science fiction

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.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

ramework

-0.33

 keyst

-0.27

-heading

-0.25

erais

-0.25

ndl

-0.25

straints

-0.24

atern

-0.24

 recl

-0.24

Īëĭ¤

-0.24

 ÑĢÐµÑģÑĤ

-0.24

POSITIVE LOGITS

åĪĽéĢłåĬĽ

0.29

åĪĽéĢł

0.29

åħ±åĪĽ

0.27

åı¤æĢª

0.26

ean

0.26

 CreateTable

0.25

åħ·ä½ĵåĨħå®¹

0.25

lius

0.25

faker

0.24

éļĪ

0.24

Activations Density 0.005%

science fiction

No Comments

No Known Activations