INDEX

Explanations

DNA

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

uye

-0.27

éģ¿

-0.26

ho

-0.26

explicit

-0.25

expo

-0.24

 Blob

-0.24

 blob

-0.24

_exp

-0.23

exp

-0.23

Layer

-0.23

POSITIVE LOGITS

ç²±

0.28

wares

0.27

wear

0.26

èĢĢ

0.25

é½Ĳ

0.25

ãģ·

0.25

 translators

0.24

/ubuntu

0.24

bam

0.24

Ø§Ø±Ø¯

0.24

Activations Density 0.012%

DNA

No Comments

No Known Activations