INDEX

Explanations

tags

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

ajs

-0.31

 Trend

-0.31

HER

-0.29

æĸ¹ä½į

-0.28

LTS

-0.28

ollo

-0.26

èĮĥ

-0.26

elenium

-0.26

èĲ¥

-0.25

HER

-0.25

POSITIVE LOGITS

 Territories

0.29

åİŁæĸĩåľ°åĿĢ

0.28

å°¾å·´

0.27

FromClass

0.26

 attach

0.26

metics

0.26

yclopedia

0.26

çĤ·

0.25

 works

0.24

kah

0.24

Activations Density 0.017%

tags

No Comments

No Known Activations