INDEX

Explanations

archeology

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

å·¡åĽŀ

-0.30

æĳ¸

-0.28

hib

-0.28

.spin

-0.27

éĢĶ

-0.27

 spinner

-0.26

di

-0.26

 spin

-0.25

ä¸ĥæĺŁ

-0.25

spin

-0.24

POSITIVE LOGITS

 anarch

0.28

laden

0.27

 Implements

0.26

ographs

0.25

archy

0.25

sticks

0.25

maids

0.25

addon

0.25

é¾Ħ

0.25

+offset

0.24

Activations Density 0.009%

archeology

No Comments

No Known Activations