INDEX

Explanations

guiding through a process

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

æŃ£å¼ı

-0.25

ESA

-0.25

éĻ¤å¤ķ

-0.24

ä¹ĺ

-0.24

.builder

-0.24

è§Ĵ

-0.24

 elder

-0.24

å®ĵ

-0.24

EP

-0.24

esco

-0.23

POSITIVE LOGITS

pend

0.32

ableObject

0.28

iod

0.26

bout

0.25

>About

0.24

åĲĦè¡Į

0.24

inic

0.24

okay

0.24

 imprint

0.24

 knob

0.23

Activations Density 0.101%

guiding through a process

No Comments

No Known Activations