INDEX

Explanations

ordering

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

ormap

-0.29

æīĺè¿Ĳ

-0.27

AdapterManager

-0.25

æĸ¹å¼ıè¿Ľè¡Į

-0.25

å¹¿å¤§

-0.25

 proxy

-0.25

 ÅŁekilde

-0.25

éĻĲåº¦

-0.24

åī¯

-0.24

@dynamic

-0.24

POSITIVE LOGITS

mares

0.29

boxes

0.27

Morning

0.26

æµĳèº«

0.25

ITIES

0.25

.JPanel

0.25

.Our

0.25

stalk

0.25

ç²Ĵ

0.25

OfDay

0.25

Activations Density 0.002%

ordering

No Comments

No Known Activations