INDEX

Explanations

life

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

hsi

-0.27

 Essence

-0.27

 tertiary

-0.26

akit

-0.26

opsis

-0.25

 Eggs

-0.25

RY

-0.25

 decrement

-0.25

gon

-0.24

çļĦå½¢è±¡

-0.24

POSITIVE LOGITS

labs

0.32

è°Īè®º

0.31

è¿Ĳæ²³

0.28

 pieces

0.27

pieces

0.27

è°ķ

0.26

éªļæī°

0.26

 Definitions

0.26

Definitions

0.26

pdf

0.25

Activations Density 0.012%

life

No Comments

No Known Activations