INDEX

Explanations

local

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

åĽŀé¦Ī

-0.29

 Important

-0.28

Important

-0.26

tph

-0.26

 Boise

-0.25

 hous

-0.25

åģľçĶµ

-0.25

uppet

-0.24

ä¸ªä½ĵ

-0.24

æĿ¥çĶµ

-0.24

POSITIVE LOGITS

 competit

0.30

pop

0.27

cal

0.27

atism

0.27

å°½æĥħ

0.26

(va

0.25

NAL

0.25

jud

0.24

udos

0.24

 competitive

0.24

Activations Density 0.002%

local

No Comments

No Known Activations