INDEX

Explanations

apt

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

 delegation

-0.27

åĲĮçŃī

-0.26

OfSize

-0.26

 fortn

-0.26

zzle

-0.25

Gal

-0.25

iente

-0.25

elled

-0.24

udent

-0.24

å¤ĦåĪĨ

-0.24

POSITIVE LOGITS

æ£ł

0.27

åĪ¶åº¦æĶ¹éĿ©

0.27

ANGO

0.27

ç»ĨèĬĤ

0.26

AFX

0.25

ä½Ĩä¹Ł

0.25

engkap

0.25

-touch

0.25

_ctx

0.24

èļĤ

0.24

Activations Density 0.004%

apt

No Comments

No Known Activations