INDEX

Explanations

Dakotas, locations, tribes

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

iew

-0.27

aras

-0.27

 setTitle

-0.27

å¹Į

-0.26

ohan

-0.25

setScale

-0.25

 trá»Ŀi

-0.24

opl

-0.24

parms

-0.24

agne

-0.24

POSITIVE LOGITS

EDURE

0.28

åħį

0.26

áº¡t

0.25

åĩ¡

0.24

Nonnull

0.24

ä¿¾

0.24

 anymore

0.24

tec

0.24

RID

0.24

 concerning

0.24

Activations Density 0.032%

Dakotas, locations, tribes

No Comments

No Known Activations