INDEX

Explanations

definitions/explanations

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

 somehow

-0.33

wald

-0.29

 caul

-0.27

raft

-0.26

 CRUD

-0.26

allet

-0.25

ulum

-0.24

 against

-0.24

leigh

-0.24

quirrel

-0.24

POSITIVE LOGITS

outube

0.29

ByVersion

0.28

 onClose

0.27

ibles

0.26

åıĮåĲĳ

0.26

åĪĨåĪ¥

0.26

olds

0.26

çŁ¿çī©

0.25

è¾¾å°Ķ

0.25

 Schro

0.25

Activations Density 2.714%

definitions/explanations

No Comments

No Known Activations