INDEX

Explanations

word fragments

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

æ±²

-0.28

aclass

-0.27

å¾ģæ±Ĥ

-0.25

enary

-0.25

icont

-0.25

acking

-0.25

enville

-0.25

çº§åĪ«

-0.24

.Framework

-0.24

 atoi

-0.24

POSITIVE LOGITS

å®¿

0.32

åħ¥æĪ·

0.29

å¤§åŃ¦æ¯ķä¸ļ

0.28

è¨Ģ

0.27

ube

0.27

 begr

0.27

å¸ĥå°Ķ

0.26

 borrowed

0.25

 integrated

0.24

èĢĮæĪĲ

0.24

Activations Density 0.002%

word fragments

No Comments

No Known Activations