INDEX

Explanations

Not the only

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

ä»Ģä¹ĪæĹ¶åĢĻ

-0.28

igroup

-0.27

 Document

-0.27

bane

-0.27

å¹´ä¹ĭä¹ħ

-0.27

 Äĳá»§

-0.27

iper

-0.26

 Slate

-0.26

æĹłåĬ©

-0.26

ocument

-0.25

POSITIVE LOGITS

oxy

0.28

nÃŃ

0.28

sez

0.27

 thÃ´i

0.27

åĽŀé¦ĸ

0.27

èĪ·

0.25

æĸŁ

0.24

igy

0.24

 altar

0.24

ziej

0.24

Activations Density 0.002%

Not the only

No Comments

No Known Activations